Terminal
1737 graded320 agent-ready3900 desk reviews by the panel51 accept x402updated 19 Nov 19:04 UTC
Also indexed, not graded 2,000 indexed MCP servers MCP registry, 67,052 servers
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/search
Filters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | AI SDKVercel · Agent framework | Frameworks | AA | 93.6 | none | n/a | n/a | Free · OSS | API key | Library | ||
|
Open-source TypeScript toolkit from Vercel for building AI applications and agents, with a provider-agnostic API, a ToolLoopAgent, an MCP client and UI hooks for React, Vue, Svelte and Angular. Top strength Apache 2.0, with 246 npm releases of Top weakness TypeScript only, and |
||||||||||||
| 2 | Vertex AI (Gemini Enterprise Agent Platform)Google Cloud · Model API | Models | AA | 91.2 | none | n/a | n/a | from $0.30 / 1M in | OAuth or key | Hosted | ||
|
Google Cloud's enterprise API for Gemini models and Model Garden partner and open models, including Claude, Llama and Qwen, on the platform formerly called Vertex AI, with regional endpoints, provisioned throughput and IAM access. Top strength No incident naming Vertex or Gemini on status.cloud.google.com between 8 July and 6 October 2026 Top weakness The SLA drops from 99.5 to 95 per cent for short-term availability models, Gemini 3.7 and 3.6 Flash among them |
||||||||||||
| 3 | OpenAI Agents SDKOpenAI · Agent framework | Frameworks | AA | 90 | 3.9 (8) | n/a | n/a | Free · OSS | API key | Library | ||
|
Multi-agent framework built on agents, hand-offs and guardrails, with sessions, tracing and human approval. Top strength MCP in about 11 lines, with static and dynamic tool filters and require_approval Top weakness Tracing on by default, with model and tool content, sent to OpenAI |
||||||||||||
| 4 | InfisicalInfisical · HTTP API | Secrets | AA | 86.7 | 3.8 (8) | n/a | n/a | Freemium | OAuth or key | Hosted and local | ||
|
Open-source secrets manager with machine identities (Universal Auth, OIDC, AWS, GCP, Azure, Kubernetes, SPIFFE), dynamic secrets, rotation and audit logs, hosted in the US or EU or self-hosted. Top strength Agent Vault and Agent Proxy attach credentials at the proxy, so the agent's context never contains them Top weakness Free has no audit logs, Pro keeps them 30 days, and dynamic secrets need Advanced at $40 an identity a month |
||||||||||||
| 5 | OpenAI APIOpenAI · Model API | Models | AA | 85.8 | 3.5 (8) | n/a | n/a | from $0.10 / 1M in | API key | Hosted | ||
|
OpenAI's API for accessing its models through Responses, Chat Completions and Batch endpoints. Top strength Official OpenAPI document and an llms.txt index Top weakness Elevated errors across the API for about 5 hours 20 minutes on 29 September and about 90 minutes on 17 September 2026 |
||||||||||||
| 6 | GPT-6.2 AstraOpenAI · Model API | Models | AA | 85.8 | none | n/a | n/a | Pay per use | API key | Hosted | ||
|
GPT-6.2 Astra is OpenAI's most capable model in its API, for demanding reasoning, coding and computer use, with a 1.05M-token context, 128K output, text and images in, at $8 input and $40 output per million tokens. Top strength $8 input and $40 output per million tokens, 20% below GPT-6 Astra, with cached input at $0.40 Top weakness Tool calling works only through the Responses API, not Chat Completions |
||||||||||||
| 7 | Pydantic AIPydantic · Agent framework | Frameworks | AA | 85.6 | 4.0 (8) | n/a | n/a | Free · OSS | None | Library | ||
|
Typed Python agent framework for 25+ model providers, with MCP, A2A and durable execution. Top strength Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model Top weakness Python only, and 3.11 or newer since 2.55.0 |
||||||||||||
| 8 | Stripe API + MCPStripe · HTTP API | Platforms | AA | 85 | 4.0 (8) | n/a | n/a | 2.9% fee | OAuth or key | Hosted and local | ||
|
Card, stablecoin and billing APIs with a hosted MCP server (mcp.stripe.com, 15 tools including generic stripe_api_read and stripe_api_write). Top strength One integration takes cards through shared payment tokens and USDC over MPP or x402, settled to the Stripe balance in fiat Top weakness Card payments from agents have a 0.50 USD minimum, so per-call micropayments must use stablecoins |
||||||||||||
| 9 | Composio (API + MCP)Composio · HTTP API | Tool access | A | 84.4 | 3.5 (8) | n/a | n/a | $29 / mo | OAuth or key | Hosted | ||
|
Tool access and per-user authentication for agents across 1,000+ apps. Top strength Seven Connect meta-tools, and sessions that load chosen toolkits or filter by read-only and destructive tags Top weakness Tool arguments and responses are logged for up to a year unless ZDR, a paid add-on, is on |
||||||||||||
| 10 | MongoDB MCP ServerMongoDB · MCP server | Databases | A | 83.9 | 3.5 (8) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
MongoDB's official MCP server for querying and managing databases and Atlas resources, with configurable tool access. Top strength
Top weakness 53 tools with Atlas credentials, and most database tool descriptions are one line |
||||||||||||
| 11 | Backblaze B2Backblaze · HTTP API | Storage | A | 83.8 | 3.8 (8) | n/a | n/a | $0.01 / GB | API key | Hosted and local | ||
|
Object storage at $6.95 a TB-month with the first 10 GB free, egress free up to three times what you store and $0.01 a GB after, and no charge for most API calls. Top strength $6.95 a TB-month, first 10 GB free, Class A, B and C API calls free, and no card at signup Top weakness EU upload failures on 30 October were reopened the same evening and still unresolved in the status feed on 31 October |
||||||||||||
| 12 | Strands AgentsAmazon Web Services · Agent framework | Frameworks | A | 83.7 | none | n/a | n/a | Free · OSS | None | Library | ||
|
Strands Agents is AWS's open-source agent SDK for Python and TypeScript. A model-driven loop runs tools, MCP servers, multi-agent patterns, sessions, interrupts for human approval and OpenTelemetry tracing, with Amazon Bedrock as the default model provider. Top strength No usage analytics found, with OpenTelemetry tracing opt-in Top weakness Three advisories in October 2026 on A2A session sharing and world-readable default session files, fixed in 1.43.0 and 1.48.0 |
||||||||||||
| 13 | Amazon BedrockAmazon Web Services · Model API | Models | A | 83.5 | none | n/a | n/a | from $0.30 / 1M in | OAuth or key | Hosted | ||
|
AWS's managed API for foundation models from Anthropic, OpenAI, Amazon, Meta, Mistral, DeepSeek, Qwen, xAI and others, called through the Converse API or OpenAI- and Anthropic-compatible endpoints under one AWS account. Top strength One API and one bill for Anthropic, OpenAI, Amazon, Meta, Mistral, DeepSeek, Qwen, xAI and other model families Top weakness An AWS account, IAM setup and a Region choice come before the first call, and an agent can't sign up alone |
||||||||||||
| 14 | Stripe IdentityStripe · HTTP API | Verification | A | 83.2 | 3.0 (4) | n/a | n/a | Pay per use | API key | Local | ||
|
Stripe Identity verifies government-issued photo IDs from more than 120 countries, matches them to selfies and validates US Social Security numbers. Sessions are created and read through the Stripe API, and the end user completes the check in Stripe's flow. Top strength Six typed Identity operations in Stripe's public OpenAPI spec, with Markdown docs and llms.txt Top weakness Document, selfie and US SSN checks only. No sanctions or watchlist screening and no business verification |
||||||||||||
| 15 | Microsoft Agent FrameworkMicrosoft · Agent framework | Frameworks | A | 83.1 | 3.0 (4) | n/a | n/a | Free · OSS | None | Library | ||
|
Microsoft Agent Framework is an open-source SDK for building AI agents and multi-agent workflows in Python and .NET, with a Go version in public preview. Microsoft names it the successor to AutoGen and Semantic Kernel. Top strength MIT, with Python 1.24.0 and .NET 1.27.0 both tagged on 30 October 2026, past 1.0 since 2 April 2026 Top weakness Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.22.0 on 15 October and 1.23.0 on 22 October 2026 |
||||||||||||
| 16 | Google Calendar APIGoogle · HTTP API | Scheduling | A | 82 | 4.0 (8) | n/a | n/a | Free | OAuth | Hosted | ||
|
Google Calendar's REST API for accessing calendars and managing events. Top strength 21 OAuth scopes, including free/busy only and read-only on owned calendars Top weakness Google calendars only |
||||||||||||
| 17 | Amazon Bedrock AgentCore MemoryAmazon Web Services · HTTP API | Memory | A | 81.6 | 3.5 (4) | n/a | n/a | $1 / GB | OAuth or key | Hosted and local | ||
|
Managed memory service for AI agents on AWS. It stores conversation events as short-term memory and extracts facts, preferences, summaries and episodes into searchable long-term records, through the AWS API, SDKs and an MCP server. Top strength IAM permissions per operation, resource-based policies and namespace condition keys, with OAuth sign-in and deny-by-default Cedar policies available through AgentCore Gateway Top weakness Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write |
||||||||||||
| 18 | Nylas Email APINylas · HTTP API | Mailboxes | A | 81.6 | 3.5 (4) | n/a | n/a | $15 / mo | OAuth or key | Hosted | ||
|
Unified email API from Nylas for reading, searching, drafting and sending mail in a person's existing Gmail, Microsoft 365, Exchange, Yahoo, iCloud or IMAP mailbox, with webhooks for new mail. A hosted MCP server exposes the same data. Top strength One schema for messages, threads, drafts, folders and attachments across Gmail, Microsoft 365, Exchange EWS, Yahoo, iCloud and IMAP Top weakness Seven status incidents on email between 6 August and 17 September 2026, including about six hours of IMAP retrieval and webhook degradation on 10 September |
||||||||||||
| 19 | Browser UseBrowser Use · HTTP API | Browser | A | 81.5 | 3.0 (4) | n/a | n/a | $0.02 / browser-hr x402 | API key | Hosted and local | ||
|
Browser Use runs AI agents that operate a web browser. It has an MIT Python library and CLI, and a hosted cloud with an agent API, managed browsers over CDP and an MCP server. Top strength x402 host at x402.api.browser-use.com takes USDC on Base with no account or API key, and wallet top-ups start at $0.01 Top weakness The privacy policy says inputs are used to train Browser Use's AI models. Self-service zero data retention covers US projects only and doesn't say what model providers keep |
||||||||||||
| 20 | MCP Toolbox for DatabasesGoogle · MCP server | Databases | A | 81.4 | none | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
MCP Toolbox for Databases is Google's open-source MCP server for more than 30 data sources, among them BigQuery, AlloyDB, Cloud SQL, Spanner and PostgreSQL. It runs as a binary or container with prebuilt or custom tools from tools.yaml. Top strength 57 source types and 39 prebuilt configurations, from BigQuery and AlloyDB to PostgreSQL, MySQL, MongoDB and Snowflake Top weakness --allowed-origins and --allowed-hosts default to *, which the docs call unsafe |
||||||||||||
| spec | Machine Payments Protocol (MPP)Tempo and Stripe · Payment protocol | Pay per call | A | 81.3 | 4.0 (2) | n/a | n/a | Free | None | Specification | ||
|
A method-agnostic 'Payment' HTTP authentication scheme from Tempo and Stripe, launched on 2026-03-18. Top strength A 1,464-line Internet-Draft with 11 error codes, Retry-After and HMAC-SHA256 test vectors Top weakness Individual Internet-Draft, not adopted by any IETF working group |
||||||||||||
| 21 | Resend API + MCPResend · HTTP API | A | 81.2 | 3.4 (8) | n/a | n/a | $20 / mo | OAuth or key | Hosted and local | |||
|
Transactional and marketing email API with inbound receiving, templates, broadcasts and automations. Top strength
Top weakness 136 MCP tools load at once, with no toolsets |
||||||||||||
| 22 | Azure OpenAI in Foundry ModelsMicrosoft · Model API | Models | A | 81.2 | none | n/a | n/a | from $0.10 / 1M in | OAuth or key | Hosted | ||
|
Microsoft Azure's hosted API for OpenAI's GPT models and other Foundry Models sold by Azure, such as DeepSeek, Llama, Mistral and Grok, called through an OpenAI-compatible v1 endpoint on each customer's Azure resource. Top strength Public OpenAPI 3.2 spec for the v1 API, 71 paths covering Responses, Chat Completions, batches, files and vector stores Top weakness Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026 |
||||||||||||
| 23 | Gmail APIGoogle · HTTP API | Mailboxes | A | 80.9 | 3.0 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
Google's REST API for Gmail mailboxes. It searches and reads messages and threads, writes drafts, sends mail, manages labels and settings, and reports mailbox changes through history records and Cloud Pub/Sub push notifications. Access is by OAuth 2.0. Top strength 14 OAuth scopes, with Top weakness Eight restricted scopes, including |
||||||||||||
| 24 | Descope Agentic Identity HubDescope · HTTP API | Agent auth | A | 80.6 | 3.1 (8) | n/a | n/a | $249 / mo | OAuth or key | Hosted | ||
|
Descope's identity and access tools for AI agents, built on its customer identity platform. Top strength Token vault for user and tenant tokens with scoped fetch, forced refresh and per-token deletion Top weakness No tool catalogue, so you write every provider call yourself |
||||||||||||
| 25 | AWS Secrets ManagerAmazon Web Services · HTTP API | Secrets | A | 80.3 | 3.9 (8) | n/a | n/a | $0.40 / mo | OAuth or key | Hosted | ||
|
Managed secrets store priced per secret and per API call, with IAM for access, KMS for encryption, CloudTrail for audit, cross-region replication and rotation either managed (RDS, Aurora, DocumentDB, Redshift) or by a Lambda function you own. Top strength IAM roles on EC2, ECS, Lambda and EKS mean no long-lived credential in the agent Top weakness Every API call is billed, so per-request reads add up and the docs push you to cache |
||||||||||||
| 26 | Bird API + MCPBird (formerly MessageBird) · HTTP API | Messaging | A | 80.3 | 3.6 (8) | n/a | n/a | Pay per use | OAuth or key | Hosted and local | ||
|
Bird's rebuilt developer API sends SMS and WhatsApp (plus email and voice) from one account, with an OpenAPI 3.1 spec, generated SDKs, a CLI and a hosted OAuth MCP server at mcp.bird.com. Top strength API keys with per-product read or write scopes, expiry and CIDR limits, and a read-only default login Top weakness No free SMS or WhatsApp allowance, and we found no way to top up the prepaid balance by API |
||||||||||||
| 27 | Basic MemoryBasic Memory LLC · MCP server | Memory | A | 80.1 | none | n/a | n/a | $19 / mo | None | Local | ||
|
Basic Memory is an open-source MCP server and CLI that keeps an AI assistant's memory as Markdown notes on the user's disk, with full-text, semantic and graph search, plus an optional paid cloud for shared team memory. Top strength 12 MCP tools, each with readOnly, destructive and idempotent hints, and Top weakness 1.0 removed every pre-1.0 tool and command with no aliases, so older agent instructions and allowlists break |
||||||||||||
| 28 | Twilio API + MCPTwilio · HTTP API | Messaging | A | 79.9 | 3.5 (8) | n/a | n/a | Pay per use | OAuth or key | Hosted and local | ||
|
Programmable Messaging (SMS, MMS, WhatsApp, RCS) and Verify over REST. Top strength Per-segment US prices, carrier fees by carrier and the $0.001 failed-message fee published without a login Top weakness US SMS at $0.0083 a segment plus $0.0035 to $0.005 in carrier fees, with inbound charged at the same rate |
||||||||||||
| 29 | Twilio Programmable Voice API + MCPTwilio · HTTP API | Calling | A | 79.9 | 3.1 (8) | n/a | n/a | $1.15 / mo | OAuth or key | Hosted and local | ||
|
Programmable Voice for placing and answering calls on Twilio numbers in 100+ countries, controlled with TwiML or REST. Top strength Twilio APIs SLA at 99.95 per cent for every paying customer, with 10 per cent credits Top weakness US outbound at $0.014 a minute, plus $0.0044 for Media Streams or $0.07 for ConversationRelay |
||||||||||||
| 30 | Mapbox APIs + MCPMapbox · HTTP API | Maps | A | 79.7 | 3.6 (8) | n/a | n/a | $0.75 / 1k req | OAuth or key | Hosted and local | ||
|
Geocoding v6 with batch, Search Box for places and categories, Directions, Matrix, Isochrone, Map Matching, route optimisation, static images and map tiles. Top strength Official MCP server, hosted at mcp.mapbox.com with OAuth or run locally, listed in the MCP registry Top weakness Storing geocodes needs the Permanent tier at $5 per 1,000, about 6.7 times the temporary rate, and a card on file |
||||||||||||
| 31 | Tavily API + MCPTavily · MCP server | Search | A | 79.5 | 3.6 (8) | n/a | n/a | $7.50 / 1k req | OAuth or key | Hosted and local | ||
|
Tavily's REST API for web search, URL extraction, site mapping, crawling and cited research reports, with the official MCP server hosted at mcp.tavily.com or run locally from npm. Top strength Keyless search and extract, plus a free 1,000 credits a month with no card Top weakness x402 covers advanced search only, not extract, map, crawl or research |
||||||||||||
| 32 | AgentOSFramers Lab, Inc. · Agent framework | Frameworks | A | 79.5 | 2.8 (4) | n/a | n/a | Free · OSS | API key | Library | ||
|
Open-source TypeScript agent framework from Framers Lab, installed from npm as @framers/agentos. It runs agents with long-term memory, multi-agent teams, graph workflows with checkpoints, guardrails and approval gates across 11 model providers. Top strength Apache 2.0, with no analytics or telemetry code found in the source and a privacy page that says the runtime sends nothing to the vendor Top weakness Version 0.15.69, with 95 release tags after 0.14.2 to 1 November 2026 and breaking minors 0.14.0 and 0.15.0 in that time |
||||||||||||
| 33 | KnockKnock · HTTP API | Notifications | A | 79.4 | 3.5 (2) | n/a | n/a | $250 / mo | OAuth or key | Hosted | ||
|
Knock is a hosted notification workflow API that sends messages across in-app feeds, push, email, SMS and chat, with batching, preferences and a hosted MCP server. Top strength Hosted MCP server with OAuth, six capability toggles and no delete tools Top weakness No Retry-After header or backoff guidance found for 429 answers |
||||||||||||
| 34 | Amazon Bedrock GuardrailsAmazon Web Services · HTTP API | Guardrails | A | 79.3 | 3.4 (8) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Configurable guardrail policies (content filters with a prompt-attack category, denied topics, word filters, PII and regex filters, contextual grounding, Automated Reasoning checks) applied to any model through the ApplyGuardrail API, or inline through InvokeGuardrailChecks. Top strength ApplyGuardrail works with any model, self-hosted or third party, without invoking Bedrock inference Top weakness Per-policy billing, so four paid policies on one request cost four times, and no Guardrails-specific free tier |
||||||||||||
| 35 | Pinecone API + MCPPinecone · HTTP API | Retrieval | A | 79.3 | 3.5 (8) | n/a | n/a | $20 / mo | API key | Hosted and local | ||
|
Managed, closed-source vector database with serverless indexes. Top strength OpenAPI files per API version, quarterly versions with at least 12 months of support each Top weakness Serverless reads in AWS us-west-2 returned 5xx errors for 11 hours on 17 September 2026 |
||||||||||||
| 36 | Cloudflare Workers OAuth ProviderCloudflare · SDK + MCP | Agent auth | A | 79.3 | none | n/a | n/a | Free · OSS | OAuth | Local | ||
|
Cloudflare Workers OAuth Provider is Cloudflare's open-source TypeScript library that adds OAuth 2.1 authorisation to HTTP APIs and remote MCP servers on Cloudflare Workers, as both the authorisation server and the resource server. Top strength Implements both the authorisation server and the resource server for MCP, with discovery, token, revocation and optional dynamic client registration Top weakness Runs only on Cloudflare Workers and needs a KV namespace bound as OAUTH_KV |
||||||||||||
| 37 | Amazon S3Amazon Web Services · HTTP API | Storage | A | 79.2 | 3.4 (8) | n/a | n/a | $0.005 / 1k req | API key | Hosted | ||
|
AWS object storage for files, backups and application data, accessed through an API. Top strength STS session credentials with session policies, so an agent can hold one prefix for an hour Top weakness Egress to the internet is billed per GB after 100 GB a month |
||||||||||||
| 38 | Claude APIAnthropic · Model API | Models | A | 79.2 | 3.5 (4) | n/a | n/a | from $0.10 / 1M in | API key | Hosted | ||
|
Anthropic's Messages API for Claude, with server-side tools, an MCP connector and computer use. Top strength Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model Top weakness Many API incidents labelled major in the 90 days to 1 November 2026, among them a critical one on 23 October and five more from 24 to 27 October |
||||||||||||
| spec | x402x402 Foundation (Linux Foundation) · Payment protocol | Pay per call | A | 79.2 | 4.5 (2) | n/a | n/a | Free · OSS | None | Specification | ||
|
Protocol for per-request stablecoin payments using HTTP 402. Top strength No account and no protocol fee, a funded wallet is enough Top weakness Five validated attacks on authorisation, binding, replay and web handling (arxiv 2605.11781) |
||||||||||||
| 39 | Claude Fable 5.2Anthropic · Model API | Models | A | 79.2 | none | n/a | n/a | Pay per use | API key | Hosted | ||
|
Claude Fable 5.2 is Anthropic's most capable generally available model, for demanding reasoning and long-running agent work, with a 1M-token context, 128K output, text and images in, at $8 input and $40 output per million tokens. Top strength $8 input and $40 output per million tokens, 20% below Fable 5.1, with cache reads at 2.5% of input Top weakness Adaptive thinking is always on and can't be turned off |
||||||||||||
| 40 | HookdeckHookdeck Technologies Inc. · HTTP API | Webhooks | A | 79.1 | 4.3 (4) | n/a | n/a | $39 / mo | API key | Hosted and local | ||
|
Hookdeck Event Gateway is a hosted service that receives webhooks, queues them and sends them on to HTTP destinations with filters, transformations, retries and replay. Agents use its REST API or the stdio MCP server in the Hookdeck CLI. Top strength API keys take read or write scopes per resource family, project and resource grants, and rollover with a 0, 1 or 24 hour overlap Top weakness Go SDK last committed 11 December 2024 and the TypeScript SDK is marked deprecated, so current clients are the CLI, Terraform and raw HTTP |
||||||||||||
| 41 | Apify MCP ServerApify · MCP server | Scrapers | A | 79 | 3.4 (8) | n/a | n/a | $1 / call x402 | OAuth or key | Hosted and local | ||
|
Exposes thousands of Apify Store Actors (scrapers, crawlers, automations) as dynamically discovered MCP tools, hosted at mcp.apify.com or run locally; supports OAuth, API tokens and agentic payments (x402 prepaid tokens, Skyfire). Top strength x402 on Apify's own domains, a prepaid token from agi.apify.com for any limited-permission Actor and x402 single runs billed at real cost Top weakness 0.19.0 and 0.20.0 (19 and 29 October 2026) changed tool behaviour with breaking changes flagged only on release day |
||||||||||||
| 42 | BlockRun.AIBlockRun, Inc. · MCP server | Models | A | 78.9 | 3.5 (2) | n/a | n/a | Pay per use x402 | OAuth or key | Local | ||
|
Model and API gateway with an OpenAI-compatible interface, MCP support and per-request stablecoin payments through x402. Top strength x402 v2 on its own gateway, USDC on Base, Solana and Arc, with no account needed Top weakness Since 21 October 2026 prompts and completions sent through the Base, Arc and API gateways are stored with no fixed expiry |
||||||||||||
| 43 | Cloudflare R2Cloudflare · HTTP API | Storage | A | 78.8 | 3.5 (8) | n/a | n/a | $0.0045 / 1k req | API key | Hosted | ||
|
S3-compatible object storage with no egress fees. Top strength Free egress and a free tier of 10 GB-month plus 1 million writes a month Top weakness No versioning, tagging, ACLs or bucket policies on the S3 API; retention comes as bucket lock rules |
||||||||||||
| 44 | Context.devContext Dev Inc. · HTTP API | Scrapers | A | 78.8 | 3.5 (4) | n/a | n/a | $19 / mo | OAuth or key | Hosted | ||
|
Context.dev, formerly Brand.dev, is a web data API that turns a URL into Markdown, HTML, screenshots or schema-shaped JSON, with crawl, map, search, batches and monitors. Scrape Anything is its scrape endpoint, also reachable through a hosted MCP server. Top strength A public OpenAPI 3.1 file covers 38 paths with operation IDs, typed request schemas and documented 400 to 500 responses Top weakness The terms let Context.dev train its models on submitted URLs, prompts and returned results unless a separate no-training or ZDR agreement applies |
||||||||||||
| 45 | ElevenLabs Voice Cloning and Voice Design APIElevenLabs · Model API | Cloning | A | 78.7 | 3.5 (2) | n/a | n/a | $6 / mo | API key | Hosted and local | ||
|
ElevenLabs' voice cloning service creates voices from audio samples. Professional cloning uses verified recordings, while Voice Design generates voices from text prompts. Top strength Instant clones from 1 to 2 minutes of audio on the $6 Starter plan Top weakness Instant clones rely on an attestation, not a check |
||||||||||||
| 46 | Google Sheets APIGoogle · HTTP API | Spreadsheets | A | 78.6 | 2.8 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
REST API from Google for reading and writing Google Sheets spreadsheets, covering cell values, ranges, formulas, formatting, tables and comments. Access is by OAuth 2.0, and a six-tool MCP server is in Developer Preview. Top strength spreadsheets.batchUpdate takes 74 request kinds, applies them atomically and counts as one request against quota Top weakness Quotas are 300 reads and 300 writes a minute per project and 60 each per user per project |
||||||||||||
| 47 | Google Cloud StorageGoogle Cloud · HTTP API | Storage | A | 78.6 | none | n/a | n/a | $0.005 / 1k req | OAuth | Hosted | ||
|
Google Cloud Storage is Google Cloud's object store for buckets and objects, reached through JSON and XML REST APIs, a gRPC Storage Control API, the gcloud CLI, client libraries and a generally available remote MCP server. Top strength Generally available MCP server since 20 April 2026, with IAM permissions per MCP method Top weakness MCP tools carry no read-only or destructive annotations and deletes need no confirmation |
||||||||||||
| 48 | OpenAI Decisions APIOpenAI · Model API | Decisions | A | 78.5 | 3.5 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
The Decisions API is an OpenAI endpoint, generally available since 22 October 2026, that reads text, images and JSON and returns typed answers with probabilities, a predicate, a choice from a fixed set or a rubric score. Top strength Three typed question kinds, predicate, choice and score, with per-option probabilities and up to 400 questions about one input in a call Top weakness One model alias, |
||||||||||||
| 49 | ZenRowsZenRows · HTTP API | Scrapers | A | 78.4 | 3.8 (8) | n/a | n/a | $19 / mo | OAuth or key | Hosted and local | ||
|
Scraping API (Fetch, formerly Universal Scraper API) with JavaScript rendering, residential proxies and anti-bot bypass, plus Extract for structured JSON, Crawl for following a site's links, Batch for bulk URL jobs and hosted Browser Sessions. Top strength No incidents in the 90 days to 1 November 2026 on a six-component Better Stack status page Top weakness The Fetch API only takes the key in the query string |
||||||||||||
| 50 | Amazon Location ServiceAmazon Web Services · HTTP API | Maps | A | 78.4 | 4.0 (4) | n/a | n/a | $0.50 / 1k req | API key | Hosted | ||
|
Amazon Location Service is AWS's API for geocoding, place search, routing and map tiles, with geofences and device tracking. Agents call regional REST endpoints with an API key or IAM credentials, or through the AWS SDKs and CLI. Top strength API keys are limited to named actions and resources, can expire, and can be restricted by referrer or mobile app identifier Top weakness The API key is sent as the |
||||||||||||
| 51 | Customer.ioPeaberry Software, Inc. d/b/a Customer.io · HTTP API | Lifecycle marketing | A | 78.4 | 3.5 (4) | n/a | n/a | $100 / mo | OAuth or key | Hosted | ||
|
Customer.io is a customer engagement platform that stores profiles and events, builds segments and sends automated email, SMS, push, in-app and WhatsApp messages. Agents reach it through REST APIs, a hosted MCP server and a command-line tool. Top strength MCP connections default to the Top weakness No idempotency key found on App API writes, transactional sends included |
||||||||||||
| 52 | MeilisearchMeilisearch · HTTP API | Retrieval | A | 78.3 | 3.5 (4) | n/a | n/a | $30 / mo | API key | Local | ||
|
Open-source search engine from Meili SAS in Paris with typo-tolerant keyword search, vector and hybrid search, filters and facets. It runs self-hosted or as Meilisearch Cloud, with a REST API, SDKs and an experimental built-in MCP route. Top strength Keyword, vector and hybrid search in one request, with Top weakness The |
||||||||||||
| 53 | Amazon Bedrock AgentCore IdentityAmazon Web Services · HTTP API | Agent auth | A | 78.2 | 3.3 (4) | n/a | n/a | $0.01 / 1k req | OAuth or key | Hosted | ||
|
Amazon Bedrock AgentCore Identity is an AWS service that gives agents workload identities, stores OAuth tokens and API keys in a token vault, and runs OAuth flows so agents can call third-party services for users or for themselves. Top strength
Top weakness No operation to revoke or delete one user's stored grant was found. |
||||||||||||
| 54 | Firecrawl MCPFirecrawl (Mendable) · MCP server | Scrapers | A | 78.1 | 3.5 (8) | n/a | n/a | $19 / mo | OAuth or key | Hosted and local | ||
|
Official Firecrawl server for scraping pages to markdown/JSON, mapping and crawling sites, web search, browser interaction, monitoring and an autonomous research agent. Top strength Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint Top weakness No x402 or other machine payment |
||||||||||||
| 55 | Speechify API Voice CloningSpeechify · Model API | Cloning | A | 78.1 | 3.6 (8) | n/a | n/a | $10 / mo | API key | Hosted | ||
|
Zero-shot voice cloning on the SpeechifyAI API from a 10 to 30 second sample, with verified spoken consent. Top strength Verified consent on every clone, phrase and speaker matched, recording kept Top weakness No cloning on the Free plan |
||||||||||||
| 56 | Deepgram Text-to-Speech (Aura-2, Flux TTS)Deepgram · Model API | TTS | A | 78.1 | 3.5 (2) | n/a | n/a | Pay per use | API key | Hosted and local | ||
|
Deepgram's text-to-speech API for generating spoken audio. Top strength OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages Top weakness Requests can be kept for training unless each one sets |
||||||||||||
| 57 | Amazon Bedrock model customisationAmazon Web Services · HTTP API | Fine-tuning | A | 78 | 3.3 (4) | n/a | n/a | Pay per use | OAuth or key | Hosted | ||
|
Managed supervised fine-tuning, reinforcement fine-tuning and distillation of Amazon Nova, Meta Llama and selected open-weight models on Amazon Bedrock, run as asynchronous jobs through the Bedrock control-plane API, the AWS SDKs and CLI, or OpenAI-compatible endpoints. Top strength
Top weakness Fine-tuning runs in us-east-1 and us-west-2 only, and each base model in one of them (two for the Titan models) |
||||||||||||
| 58 | Nylas Calendar and Scheduler APINylas · HTTP API | Scheduling | A | 78 | 3.0 (2) | n/a | n/a | $15 / mo | OAuth or key | Hosted | ||
|
Unified calendar API over Google, Microsoft 365 and Outlook, Exchange (EWS) and iCloud. Top strength One schema across Google, Microsoft 365, Exchange EWS, iCloud and virtual calendars Top weakness Application API keys still reach every grant, and the IAM pages name no calendar permission |
||||||||||||
| 59 | MastraKepler Software, Inc. · Agent framework | Frameworks | A | 78 | none | n/a | n/a | Free · OSS | API key | Library | ||
|
Open-source TypeScript framework from Mastra for building agents and workflows, with memory, RAG, evals, tracing, an MCP client and server, and a local Studio. An optional hosted platform runs deployments and observability. Top strength MCP client with requireToolApproval per server or per tool, allowedHosts and a curated environment for stdio servers Top weakness Malicious versions of Mastra npm packages, including @mastra/core 1.42.1, were published on 17 June 2026 |
||||||||||||
| 60 | AhaSend API + MCPAhaSend · HTTP API | BB | 77.9 | 4.0 (4) | n/a | n/a | $10 / mo | OAuth or key | Hosted | |||
|
AhaSend is a Dutch email service with a REST API, SMTP relay, CLI and SDKs for transactional email and campaigns, hosted in the EU. Its hosted MCP server lets an AI tool send, diagnose and manage the account. Top strength API keys scoped per action and per sending domain, with IP allow lists and sandbox-only keys Top weakness 91 MCP tools when a connection has every scope, with no enums or numeric limits in the input schemas |
||||||||||||
| 61 | Google Maps Platform + Grounding Lite MCPGoogle · HTTP API | Maps | BB | 77.9 | 2.5 (2) | n/a | n/a | $5 / 1k req | OAuth or key | Hosted | ||
|
Geocoding, Places API (New) for text, nearby and detail search, Routes for routes and matrices, Address Validation, static maps and map tiles. Top strength Maps Experience agent tools (formerly Grounding Lite) are hosted over MCP and take an X-Goog-Api-Key header or OAuth with the maps-platform.mapstools scope Top weakness Free monthly caps beyond the prototyping Demo Key need a Cloud billing account with a payment method |
||||||||||||
| 62 | Google Drive API + MCPGoogle · HTTP API | Storage | BB | 77.8 | 3.4 (8) | n/a | n/a | Free | OAuth | Hosted | ||
|
REST API for a user's or a Workspace organisation's Drive, files, folders, permissions and share links, with resumable uploads and change feeds. Top strength No charge for API calls within quota, counted in quota units per minute per project and per user Top weakness OAuth consent, scope verification and a Cloud project before an agent can list a folder |
||||||||||||
| 63 | DiditDidit Identity Spain, S.L. · HTTP API | Verification | BB | 77.8 | 4.0 (4) | n/a | n/a | $0.15 / tx | OAuth or key | Hosted and local | ||
|
Didit is a hosted identity verification service for document, liveness, face match, sanctions screening and business registry checks. Developers reach it through a REST API with an OpenAPI spec, a hosted MCP server and client SDKs. Top strength An account and API key can be created by API at Top weakness Session deletion responses changed from 204 to 200 in August 2026 and batch deletions of over 20 sessions to 202 in October, each announced only in that month's changelog |
||||||||||||
| 64 | ElevenLabs Text to Speech API + MCPElevenLabs · Model API | TTS | BB | 77.8 | 3.5 (2) | n/a | n/a | $6 / mo | OAuth or key | Hosted and local | ||
|
ElevenLabs text-to-speech over REST, HTTP streaming and WebSocket. Top strength Keys can be limited to chosen endpoints, IP ranges and a credit quota, and service accounts hold keys that don't belong to a person Top weakness Content may be used for training unless you opt out under Data use, though the Eleven v4 launch page says it isn't used without consent |
||||||||||||
| 65 | Robot FrameworkRobot Framework Foundation · Agent framework | Desktop | BB | 77.7 | 4.0 (4) | n/a | n/a | Free · OSS | None | Library | ||
|
Robot Framework is an open-source automation framework for test automation and robotic process automation, run from the `robot` command line or Python. Its keyword libraries reach browsers, desktop applications and mobile apps. Top strength Version 7.5 of 14 September 2026, marked Production/Stable on PyPI, with Python 3.8 to 3.15 listed Top weakness Desktop and mobile control depend on separate libraries, such as AppiumLibrary and AutoItLibrary, maintained outside the core project |
||||||||||||
| 66 | TempoTempo · HTTP API | Platforms | BB | 77.6 | 3.1 (8) | n/a | n/a | $0.0006 / tx | OAuth or key | Hosted | ||
|
A payments-first Layer 1 chain incubated by Stripe and Paradigm, live on mainnet since 2026-03-18. Top strength api.tempo.xyz accepts MPP on its anonymous endpoints, so an agent can pay per request without an account Top weakness The API versioning page says endpoints are not yet stable and may change without notice |
||||||||||||
| 67 | Sequential Thinking (MCP reference server)MCP project (reference servers) · MCP server | Reasoning | BB | 77.5 | 3.0 (2) | n/a | n/a | Free · OSS | None | Local | ||
|
Single-tool reference server (`sequentialthinking`) that structures step-by-step reasoning with numbered thoughts, revisions and branches; no external calls. Top strength No network access, no credentials and no side effects beyond an in-memory history Top weakness Every thought is a tool call, so turns and tokens add up without creating anything outside the model |
||||||||||||
| 68 | Shopify API + MCPShopify · HTTP API | Commerce | BB | 77.4 | 3.6 (8) | n/a | n/a | $39 / mo | OAuth or key | Local | ||
|
Hosted commerce platform for online stores. Top strength Typed GraphQL schemas with quarterly versions supported at least 12 months Top weakness Closed platform. You can't self-host or change checkout internals |
||||||||||||
| 69 | Docker AgentDocker · Agent framework | Frameworks | BB | 77.4 | 2.8 (4) | n/a | n/a | Free · OSS | None | Library | ||
|
Docker's open-source runtime for building and running AI agents from YAML or HCL files, formerly cagent. It runs as a `docker agent` CLI plugin with a terminal UI, headless mode, HTTP, MCP and A2A servers, and a Go library. Top strength An agent with one MCP server is eight lines of YAML, with a published JSON Schema for the config Top weakness Usage telemetry is on by default and command events can include prompts passed as arguments |
||||||||||||
| 70 | OpenAI CodexOpenAI · Agent harness | Harnesses | BB | 77.3 | 3.0 (2) | n/a | n/a | $20 / mo | OAuth or key | Local | ||
|
OpenAI's coding agent for software development tasks. Top strength Sandbox on by default on macOS, Linux and Windows, with the network off and Top weakness Pre-1.0 at 0.166.0, with a minor every few days and no breaking-change section in release notes --yolo undoes both”All 2 reviews ›
|
||||||||||||
| 71 | Claude Mythos 5.2Anthropic · Model API | Models | BB | 77.3 | none | n/a | n/a | Pay per use | API key | Hosted | ||
|
Claude Mythos 5.2 is the same model as Claude Fable 5.2 without Fable's stronger cyber and biology safeguards, for organisations Anthropic verifies, with a 1M-token context, text and images in, at $8 and $40 per million tokens. Top strength $8 input and $40 output per million tokens, 20% below Fable 5.1, with cache reads at 2.5% of input Top weakness Only for organisations Anthropic verifies, so an agent can't start on it alone |
||||||||||||
| 72 | Amazon PollyAmazon Web Services · Model API | TTS | BB | 77.2 | 4.0 (8) | n/a | n/a | Pay per use | API key | Hosted | ||
|
AWS's speech synthesis API with four engines (standard, neural, long-form and generative) and 116 voices in 42 languages and variants. Top strength IAM policies scope access per action and resource, and CloudTrail logs each call Top weakness AWS may store and use text to improve the service, possibly outside the Region, unless the organisation sets an AI services opt-out policy |
||||||||||||
| 73 | You.com APIsYou.com · HTTP API | Search | BB | 77.2 | 3.8 (8) | n/a | n/a | $5 / 1k req | OAuth or key | Hosted and local | ||
|
Web Search, Contents, Answer, Research and Finance Research APIs, an OpenAI- and Anthropic-compatible Inference Router, and a hosted MCP server with six tools. Top strength x402 and MPP on Web Search and Finance Research, with no account needed Top weakness Two API hosts. Answer and Research return 'Missing Authentication Token' on ydc-index.io |
||||||||||||
| 74 | Amazon Nova Multimodal EmbeddingsAmazon Web Services · HTTP API | Embeddings | BB | 77.1 | 3.3 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Amazon Nova Multimodal Embeddings is an AWS model on Amazon Bedrock that turns text, images, document images, video and audio into vectors in one space, at 256, 384, 1024 or 3072 dimensions, through synchronous and asynchronous calls. Top strength Text, images, document images, video and audio share one vector space, with four output sizes from 256 to 3072 Top weakness In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile |
||||||||||||
| 75 | Azure Blob StorageMicrosoft · HTTP API | Storage | BB | 77.1 | 3.0 (4) | n/a | n/a | $0.005 / 1k req | OAuth or key | Hosted | ||
|
Microsoft Azure's object storage for files, backups and application data. Agents call a REST API or the Azure SDKs on a storage account, signing in with Microsoft Entra ID, an account key or a shared access signature. Top strength Microsoft Entra ID roles such as Storage Blob Data Reader can be assigned on one container, with no stored key for workloads on Azure Top weakness Shared Key authorisation with the account's access keys is allowed until the owner sets |
||||||||||||
| 76 | Google Ads APIGoogle · HTTP API | Advertising | BB | 77.1 | 3.5 (4) | n/a | n/a | Free | OAuth | Hosted and local | ||
|
Google's API for managing Google Ads accounts, campaigns, budgets, audiences, ads and performance reports over gRPC or REST, with OAuth 2.0 access. Google also publishes an open-source, read-only MCP server that runs Google Ads Query Language reports. Top strength
Top weakness One OAuth scope, |
||||||||||||
| 77 | Microsoft Execution ContainersMicrosoft · SDK + MCP | Sandboxes | BB | 77.1 | 3.0 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
Microsoft Execution Containers (MXC) is an open-source SDK for running untrusted code in a local sandbox on Windows, Linux and macOS. An application embeds it through Node.js, .NET or Rust and sets filesystem, network and UI policy for each run. Top strength MIT licence, with SDKs for Node.js, .NET and Rust all at 1.0.1 and the native runtime bundled in the npm and NuGet packages Top weakness 1.0.1, the newest release on 1 November 2026, still grants read access to the whole system drive from the Windows tool-discovery helper when PowerShell is on PATH, fixed on main only |
||||||||||||
| 78 | Web Search Tool on Amazon Bedrock AgentCoreAmazon Web Services · MCP server | Search | BB | 77.1 | 3.3 (4) | n/a | n/a | $7 / 1k req | OAuth or key | Hosted | ||
|
Web Search Tool on Amazon Bedrock AgentCore is AWS's managed web search for agents, backed by an Amazon-operated index and knowledge graph. It runs as a connector on an AgentCore Gateway and is called as an MCP tool. Top strength One tool with three inputs, Top weakness No error responses for the tool are documented. The only response example has |
||||||||||||
| 79 | Gemini Exchange APIGemini Trust Company, LLC · HTTP API | Exchanges | BB | 77.1 | none | n/a | n/a | 0.6% fee | OAuth or key | Local | ||
|
Gemini's exchange API for spot, margin, perpetuals, prediction markets and staking, through REST, WebSocket and FIX, with API key roles or OAuth, plus an official MCP server and SDKs from its developer-platform repository. Top strength Key roles enforce least privilege, since Trader cannot withdraw, Fund Manager cannot trade, Auditor is read-only, and a 403 Top weakness Client order ids are only recommended to be unique and no duplicate rejection is documented, so a retried order can execute twice |
||||||||||||
| 80 | GroqCloudGroq · Model API | Models | BB | 77 | 3.5 (8) | n/a | n/a | from $0.075 / 1M in | API key | Hosted | ||
|
OpenAI-compatible inference API serving open-weight models on Groq's processors. Top strength Free plan with no card, at 30 requests a minute and 1,000 a day on gpt-oss Top weakness Four model shutdown dates between 2026-07-17 and 2026-09-21, with no stated minimum notice |
||||||||||||
| 81 | OrbOrb, Inc. · HTTP API | Platforms | BB | 77 | 2.0 (4) | n/a | n/a | $6 / credit | API key | Hosted | ||
|
Orb is a hosted billing platform for usage-based, seat-based and hybrid pricing. It ingests usage events, computes metrics, and runs plans, subscriptions, prepaid credits and invoices through a REST API with SDKs in six languages. Top strength Public OpenAPI 3.1 description with 160 operations and 117 webhook events, plus llms.txt and a Markdown twin of every docs page Top weakness Audit logs are in private preview and limited to the Enterprise plan |
||||||||||||
| 82 | ScrapflyScrapfly (Joam Intelligence, LLC) · HTTP API | Scrapers | BB | 77 | 4.0 (2) | n/a | n/a | $30 / mo | OAuth or key | Hosted and local | ||
|
Scrape API with datacenter or residential proxies, JS rendering and an anti-bot Unblocker, plus screenshot, LLM extraction, crawler and hosted Cloud Browser APIs on one credit balance. Top strength Error catalogue of 100+ ERR:: codes, each with HTTP status, retryable and billed flags and a doc link Top weakness The open-source MCP server registers 62 tools at once, a heavy tools/list |
||||||||||||
| 83 | Google Cloud Secret ManagerGoogle Cloud · HTTP API | Secrets | BB | 76.9 | 3.6 (8) | n/a | n/a | $0.06 / mo | OAuth | Hosted | ||
|
Google Cloud's managed service for storing and accessing application secrets. Top strength Workload identity on GKE, Cloud Run and GCE, so no key in the agent, and API keys are refused Top weakness Managed rotation only covers Cloud SQL; other rotation is a Pub/Sub notification you handle |
||||||||||||
| 84 | Amazon TranslateAmazon Web Services · HTTP API | Translation | BB | 76.9 | 4.0 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
AWS's neural translation API across 75 languages. Top strength IAM policies scope access per action and resource, with a Top weakness AWS may store and use text to improve Amazon AI services unless the organisation sets an opt-out policy |
||||||||||||
| 85 | Deepgram Speech-to-Text (Nova-3, Flux)Deepgram · Model API | STT | BB | 76.9 | 3.5 (2) | n/a | n/a | Pay per use | API key | Hosted and local | ||
|
Deepgram's speech-to-text API for recorded audio and live streams, including turn detection for voice agents. Top strength Flux streams with model-level end-of-turn detection, so a voice agent needs no separate VAD Top weakness Training on audio is the default and the opt-out is a per-request flag |
||||||||||||
| 86 | OpenAI Speech to TextOpenAI · Model API | STT | BB | 76.8 | 3.3 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
OpenAI's speech-to-text API. It transcribes uploaded audio files through `/v1/audio/transcriptions`, translates recordings into English through `/v1/audio/translations`, and transcribes live audio in Realtime transcription sessions over WebSocket or WebRTC. Top strength
Top weakness
|
||||||||||||
| 87 | DatoCMSDato Srl · HTTP API | CMS | BB | 76.7 | 3.5 (4) | n/a | n/a | Freemium | OAuth or key | Hosted | ||
|
DatoCMS is a hosted headless CMS from Dato Srl in Milan. Agents write records, assets, locales and schema through the REST Content Management API, the `datocms` CLI or a hosted MCP server, and read through a GraphQL Content Delivery API. Top strength Machine-readable JSON Hyper-Schema at Top weakness No idempotency keys in the reviewed documentation. Safe retries rest on optimistic locking and the JavaScript client's automatic retry |
||||||||||||
| 88 | TemporalTemporal Technologies · Platform | Human approval | BB | 76.6 | 3.6 (8) | n/a | n/a | $0.05 / 1k calls | OAuth or key | Local | ||
|
Open-source durable execution platform with SDKs in Go, Java, Python, TypeScript, .NET, PHP, Ruby and Rust, run yourself or on Temporal Cloud. Top strength Waits of any length with a timeout survive worker restarts and deploys Top weakness No reviewer inbox, notifications or routing, so the human side is all your code |
||||||||||||
| 89 | Typesense API + MCPTypesense · HTTP API | Retrieval | BB | 76.6 | 3.0 (2) | n/a | n/a | $0.09 / GB | OAuth or key | Hosted | ||
|
Open-source (GPL-3.0) search engine with typo-tolerant keyword search, vector and hybrid search, filters, facets, geo search, JOINs and built-in embedding. Top strength Keyword, vector and hybrid search with filters, facets, sorting and geo in one request Top weakness Server v30.2 from April 2026 is still the newest stable release |
||||||||||||
| 90 | Vercel SandboxVercel · HTTP API | Sandboxes | BB | 76.6 | 3.5 (2) | n/a | n/a | $0.128 / vCPU-hr | OAuth or key | Hosted | ||
|
Firecracker microVM sandboxes on Vercel, driven from the `@vercel/sandbox` JavaScript SDK, the Python `vercel` package, a CLI or the REST API. Top strength Active CPU billing, so waiting on model responses costs only memory Top weakness Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team |
||||||||||||
| 91 | Amazon EventBridgeAmazon Web Services · HTTP API | Webhooks | BB | 76.5 | 3.3 (4) | n/a | n/a | $0.18 / GB | OAuth or key | Hosted | ||
|
Amazon EventBridge is AWS's serverless event bus. Applications, AWS services and SaaS partners publish events, and the bus routes them to targets such as Lambda functions, SQS queues and HTTPS endpoints. It includes Pipes, a scheduler and a schema registry. Top strength Smithy models published for both APIs, 57 Classic operations and 25 for the Custom Event Bus, with llms.txt and a Markdown twin of each guide page Top weakness Classic |
||||||||||||
| 92 | Cloudflare AI SearchCloudflare · HTTP API | Retrieval | BB | 76.5 | 3.5 (4) | n/a | n/a | $0.75 / 1k req | OAuth or key | Local | ||
|
Cloudflare's managed retrieval service, formerly AutoRAG, indexes websites, R2 buckets and uploaded files and answers natural-language queries with vector, keyword or hybrid search, through a REST API, a Workers binding or a per-instance MCP endpoint. Top strength Hybrid vector and BM25 search on by default, with metadata filters applied before retrieval Top weakness Public endpoints, including MCP, answer anyone with the URL unless a custom domain sits behind Cloudflare Access |
||||||||||||
| 93 | LiveKit AgentsLiveKit Incorporated · Agent framework | Voice agents | BB | 76.5 | 3.0 (4) | n/a | n/a | Free · OSS | API key | Library | ||
|
LiveKit Agents is LiveKit's open-source Python and Node.js framework for realtime voice and video agents that join LiveKit rooms, with STT, LLM, TTS and realtime-model plugins, turn detection, MCP tools and telephony through LiveKit SIP. Top strength Apache-2.0 Python and Node.js packages, with 18 Python releases in the 90 days to 1 November 2026 Top weakness The turn-detector models are under a proprietary licence that forbids use outside LiveKit Agents and training other models on their output |
||||||||||||
| 94 | Saleor API + MCPSaleor · HTTP API | Commerce | BB | 76.5 | 3.5 (2) | n/a | n/a | $1599 / mo | OAuth or key | Local | ||
|
Open-source headless commerce with a single GraphQL API for products, channels, checkouts, orders and customers, self-hosted or on Saleor Cloud. Top strength One GraphQL schema with 78 typed error-code enums and 464 marked deprecations Top weakness The MCP server can't create checkouts or orders |
||||||||||||
| 95 | HubSpot API + MCPHubSpot · HTTP API | CRM | BB | 76.4 | 4.0 (2) | n/a | n/a | $20 / seat-mo | OAuth or key | Hosted and local | ||
|
HubSpot's CRM REST API (objects, associations, search, properties, pipelines, engagements, webhooks) and its official MCP servers. Top strength Remote MCP server GA since 13 April 2026, OAuth 2.1 with PKCE only Top weakness Ten partial incidents in the 90 days to 1 November 2026, including about 8 hours of Salesforce integration outage and 3 h 15 min in North America on 23 October |
||||||||||||
| 96 | Azure AI Speech speech-to-textMicrosoft · Model API | STT | BB | 76.3 | 3.3 (8) | n/a | n/a | Freemium | OAuth or key | Hosted | ||
|
Azure's speech-to-text service for transcribing audio. Top strength Real-time and fast transcription audio isn't stored, and customer audio isn't used for training Top weakness MAI-Transcribe-2 and MAI-Transcribe-2-Streaming are preview with no SLA, and both introductory prices end with 2026 |
||||||||||||
| 97 | AWS End User MessagingAmazon Web Services · HTTP API | Messaging | BB | 76.3 | 2.5 (4) | n/a | n/a | $1 / mo | OAuth or key | Hosted | ||
|
AWS's messaging service for SMS, MMS, RCS, WhatsApp, voice and push, formerly the channel APIs of Amazon Pinpoint. Agents call the SMS and Voice v2 API or the Social Messaging API with IAM-signed requests, through the AWS CLI or SDKs. Top strength IAM policies per action and resource with condition keys and temporary credentials, and CloudTrail data events for the send actions Top weakness Sandbox limits new accounts to $1 of SMS a month and ten verified numbers until a support case per Region is approved |
||||||||||||
| 98 | Chrome DevTools MCPGoogle (Chrome DevTools team) · MCP server | Browser | BB | 76.2 | 3.5 (8) | n/a | n/a | Free · OSS | None | Local | ||
|
Lets coding agents control and inspect a live Chrome instance. Top strength Performance traces, network inspection, heap snapshots and Lighthouse audits in one server Top weakness Usage statistics go to Google by default until you pass |
||||||||||||
| 99 | Supabase API + MCPSupabase · HTTP API | Databases | BB | 76.2 | 3.3 (8) | n/a | n/a | $25 / mo | OAuth or key | Hosted and local | ||
|
Hosted Postgres with an auto-generated REST API (PostgREST), GraphQL, auth, storage, realtime and Edge Functions, plus a Management API and an official MCP server. Top strength OAuth 2.1 with dynamic client registration, plus personal access tokens scoped to chosen projects and permissions Top weakness The status feed lists 3 critical and 6 major platform incidents between 31 August and 31 October 2026, three of the majors on 21 and 22 October |
||||||||||||
| 100 | Auth0 for AI Agents (Token Vault)Auth0 by Okta · HTTP API | Agent auth | BB | 76.2 | 3.5 (2) | n/a | n/a | Freemium | OAuth | Hosted and local | ||
|
Auth0's identity and authorisation tools for AI agents, built on its identity platform. Top strength Standard grants throughout, RFC 8693 token exchange, CIBA with RAR and DPoP Top weakness Only works when Auth0 is the identity provider for your users |
||||||||||||
| 101 | HeyGen VoiceHeyGen · Model API | TTS | BB | 76.1 | 3.5 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
HeyGen Voice is HeyGen's in-house text-to-speech model, `heygen-voice-1` with a Turbo variant, which speaks HeyGen's public voices or voices cloned from one recording (instant) or 20 minutes or more (professional), through HeyGen's v3 API. Top strength OpenAPI 3.1 file with enums, ranges, Top weakness 30 requests a minute per workspace member on the speech endpoints by default, and Turbo Free's shared capacity can return 429 below that |
||||||||||||
| 102 | Amazon TextractAmazon Web Services · HTTP API | Documents | BB | 76 | 3.0 (4) | n/a | n/a | $1.50 / 1k pages | API key | Hosted | ||
|
Amazon Textract is AWS's document OCR and analysis API. It reads printed and handwritten text from scans and PDFs and returns tables, form fields, layout elements, answers to queries, and invoice, receipt and identity document fields as JSON. Top strength IAM policies grant single operations such as Top weakness AWS may store and use processed documents to improve the service, in other Regions too, unless an AI services opt-out policy is set on the AWS organisation |
||||||||||||
| 103 | Turnkey Agentic WalletsTurnkey Global, Inc. · HTTP API | Wallets | BB | 76 | 3.0 (4) | n/a | n/a | $0.10 / call | API key | Hosted | ||
|
Turnkey's signing API gives an AI agent its own non-root user and P-256 key over a company wallet. Policies evaluated in secure enclaves set what the agent may sign, and can require a person's approval. Top strength Non-root users have no permissions until an ALLOW policy exists, and any matching DENY policy wins Top weakness Documented policy conditions cap value per transaction only. Rolling-window Velocity Controls appear in the SDK clients but not in the docs |
||||||||||||
| 104 | Arize PhoenixArize AI · HTTP API | Evals | BB | 75.8 | 3.8 (8) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Self-hosted tracing, evaluation, datasets, experiments and prompt management built on OpenTelemetry and OpenInference. Top strength Free and self-hosted with no feature gating, from Top weakness Auth stays off on a loopback bind, and the default admin password is |
||||||||||||
| 105 | Parallel Search and Task APIsParallel Web Systems · HTTP API | Search | BB | 75.7 | 3.6 (8) | n/a | n/a | $1 / 1k req | OAuth or key | Hosted | ||
|
Parallel's web APIs for agents, covering search, page extraction, asynchronous research tasks, closed-ended decisions answered from current web evidence and an OpenAI-compatible Responses endpoint, with hosted Search and Task MCP servers. Top strength Fast-mode search at $1 per 1,000 with 10 excerpted results, and Extract at $1 per 1,000 URLs Top weakness Search defaults to advanced mode at $5 per 1,000 when |
||||||||||||
| 106 | Microsoft Entra Agent IDMicrosoft · HTTP API | Agent auth | BB | 75.7 | 2.8 (4) | n/a | n/a | $15 / seat-mo | OAuth | Hosted | ||
|
Microsoft Entra Agent ID is an identity type for AI agents in Microsoft Entra ID. Agents get their own directory identity, request OAuth 2.0 tokens autonomously or on behalf of a user, and are managed through Microsoft Graph. Top strength Agent identities can't hold credentials. The blueprint authenticates with a managed identity, certificate or secret and exchanges for the agent's token Top weakness Conditional Access, ID Protection and governance for agents need Microsoft Agent 365, listed at $15 a user a month on yearly billing |
||||||||||||
| 107 | Akeyless (SecretlessAI and MCP server)Akeyless · Platform | Secrets | BB | 75.6 | 3.0 (2) | n/a | n/a | Freemium | OAuth or key | Hosted and local | ||
|
SaaS secrets and machine-identity platform with a self-hosted Gateway that brokers access. Top strength Gateway-brokered SecretlessAI and a runtime-authority MCP server with 4 tools that return results, not credentials Top weakness No published prices above the free plan; clients and transactions are metered with overage billed at the end of a 12-month contract |
||||||||||||
| 108 | Azure AI Speech text-to-speechMicrosoft · Model API | TTS | BB | 75.6 | 3.5 (2) | n/a | n/a | $960 / mo | OAuth or key | Hosted | ||
|
Azure's text-to-speech service for generating spoken audio. Top strength Real-time synthesis keeps neither the input text nor the output audio Top weakness An Azure subscription needs a card, even for the free F0 tier |
||||||||||||
| 109 | Amazon SESAmazon Web Services · HTTP API | BB | 75.5 | 3.3 (8) | n/a | n/a | $105 / mo | OAuth or key | Hosted | |||
|
AWS's email service for sending and receiving at scale, over the SES v2 API or SMTP, with templates, configuration sets, receipt rules and deliverability tooling. Top strength $0.10 per 1,000 emails a la carte, falling to $0.11 per 1,000 above 100 million on Essentials Top weakness Sandbox limits new accounts to verified recipients and 200 messages a day until production access is granted |
||||||||||||
| 110 | Amazon TranscribeAmazon Web Services · Model API | STT | BB | 75.5 | 4.0 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Amazon Transcribe is AWS's speech-to-text API, with batch jobs that read audio from Amazon S3 and real-time streaming over HTTP/2 or WebSocket, signed with IAM credentials. Top strength $0.006 a minute batch and $0.01 streaming in US East, with diarisation, custom vocabulary and language ID included Top weakness AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set |
||||||||||||
| 111 | ElevenLabs Scribe Speech to Text APIElevenLabs · Model API | STT | BB | 75.5 | 3.5 (2) | n/a | n/a | Freemium | API key | Hosted and local | ||
|
ElevenLabs' speech-to-text service for audio transcription. Top strength $0.22 an hour for batch with 90+ languages and diarisation to 32 speakers Top weakness Audio may be used for training unless the account opts out, and the opt-out isn't retroactive |
||||||||||||
| 112 | OpenAI embeddingsOpenAI · HTTP API | Embeddings | BB | 75.5 | 4.5 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
OpenAI's text embedding API, with adjustable output dimensions for search and retrieval applications. Top strength text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API Top weakness No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff |
||||||||||||
| 113 | Klaviyo API + MCPKlaviyo, Inc. · HTTP API | Lifecycle marketing | BB | 75.4 | 3.8 (4) | n/a | n/a | $20 / mo | OAuth or key | Hosted and local | ||
|
Klaviyo is a marketing platform that holds customer profiles and events and sends email, SMS, WhatsApp and push campaigns and flows. Agents reach it through a JSON:API REST API and an official hosted MCP server. Top strength Public OpenAPI 3.0.2 description of 436 operations, each with its rate limit and required scopes, in an MIT repository updated on 31 October 2026 Top weakness No approval or confirmation step before |
||||||||||||
| open | Qwen3-Embedding-8BAlibaba (Qwen team) · Open-weight model | Embeddings | BB | 75.4 | 3.5 (4) | n/a | n/a | Free | None | Local | ||
|
Qwen3-Embedding-8B is Alibaba's open-weight text embedding model built on Qwen3-8B-Base, returning vectors of up to 4,096 dimensions for retrieval, code search and clustering in over 100 languages, under Apache 2.0. Top strength Among the top five on MTEB's multilingual and English tabs on 1 November 2026, results the publisher submitted Top weakness No change to the files or reference code since July 2025, and no reply from Qwen to any of its 19 questions |
||||||||||||
| 114 | ZoomInfo API + MCPZoomInfo Technologies LLC · HTTP API | Leads | BB | 75.4 | 3.0 (4) | n/a | n/a | $0.38 / credit | OAuth | Hosted | ||
|
ZoomInfo sells B2B company, contact and buying-signal data. Agents search and enrich records through a REST API with OAuth 2.0, a hosted MCP server and the GTM CLI, all drawing on one credit pool. Top strength Free account with 1,000 data credits and 1,000 AI credits, no card, covering the API, MCP server and CLI Top weakness The Licence Terms and Conditions bar disclosing benchmark results and automated access outside ZoomInfo's own tools without written approval |
||||||||||||
| 115 | SuprSendSuprSend · HTTP API | Notifications | BB | 75.4 | 3.0 (2) | n/a | n/a | $100 / mo | API key | Hosted and local | ||
|
Notification workflow API for email, SMS, push, an in-app Inbox, Slack, Microsoft Teams and webhooks, with digests, batching and preferences per user and per tenant, and a hosted MCP server. Top strength Hosted MCP server with OAuth sign-in, workspace pinning in the URL, a Top weakness No rate-limit page or 429 guidance |
||||||||||||
| 116 | Telnyx API + MCPTelnyx · HTTP API | Messaging | BB | 75.4 | 3.5 (2) | n/a | n/a | Pay per use | API key | Hosted and local | ||
|
Carrier-owned CPaaS with SMS, MMS, RCS and WhatsApp on one REST API, plus an official hosted MCP server at api.telnyx.com/v2/mcp and a stdio MCP package. Top strength US long code SMS $0.004 a part outbound and inbound, published with carrier fees and as machine-readable pricing.md Top weakness No per-key scopes or read-only keys, and the MCP can send or buy numbers without confirmation |
||||||||||||
| 117 | CosmicCosmic Inc. · HTTP API | CMS | BB | 75.4 | none | n/a | n/a | $99 / mo | API key | Hosted and local | ||
|
Cosmic is a hosted headless CMS with a REST API, a TypeScript SDK, a CLI and a hosted MCP server. Agents read and write objects, media and object types, generate media, and can create a project by agent signup. Top strength Agent signup API provisions a project and bucket with keys, idempotent per email and agent Top weakness No SOC 2, ISO 27001 or HIPAA certification, by the security page's own statement |
||||||||||||
| 118 | SanitySanity US Inc. and Sanity AS · HTTP API | CMS | BB | 75.2 | 3.3 (4) | n/a | n/a | $15 / seat-mo | OAuth or key | Hosted | ||
|
Sanity is a hosted headless CMS. Content is stored as JSON documents in the Content Lake, queried with GROQ and edited in the open-source Sanity Studio. Agents reach it through the HTTP API or the hosted MCP server at mcp.sanity.io. Top strength 26 public OpenAPI specs covering 225 operations at www.sanity.io/docs/api/openapi, plus llms.txt and a Markdown copy of every documentation page Top weakness Schema validation rules run in Sanity Studio and, since October 2026, in MCP writes. The HTTP mutation API accepts a document without checking them |
||||||||||||
| 119 | OpenAI Agents APIOpenAI · HTTP API | Harnesses | BB | 75.2 | none | n/a | n/a | Pay per use | API key | Hosted | ||
|
The OpenAI Agents API runs OpenAI's managed Codex harness as a hosted service. One call creates a session with a model, tools, MCP servers, subagents and an OpenAI-hosted or self-hosted sandbox, and OpenAI runs the loop. Top strength One session call configures the model, tools, MCP servers, subagents and the sandbox, and OpenAI runs and recovers the loop Top weakness Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date |
||||||||||||
| 120 | Cohere Embed and RerankCohere · HTTP API | Embeddings | BB | 75 | 3.5 (2) | n/a | n/a | Freemium | API key | Hosted | ||
|
Cohere's Embed API turns text, images and mixed text-and-image inputs such as PDF pages into vectors with Embed 5 Pro and Fast, and its Rerank API reorders search results with Rerank 5. Top strength Embed 5 Pro and Fast share one embedding space, so a Pro index answers Fast queries Top weakness Terms, training notice and security page disagree on whether API data trains models or goes to third parties |
||||||||||||
| 121 | gooseAgentic AI Foundation (originally Block) · Agent harness | Harnesses | BB | 75 | 2.5 (2) | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source general-purpose agent written in Rust, with a desktop app, a CLI and an embeddable server. Top strength Telemetry off until the user opts in, with the collected fields listed Top weakness Autonomous mode, which approves every tool call, is the default |
||||||||||||
| 122 | Neon MCP ServerNeon (Databricks) · MCP server | Databases | BB | 75 | none | n/a | n/a | $0.106 / unit | OAuth | Hosted | ||
|
Neon's official remote MCP server at mcp.neon.tech/mcp lets agents manage Neon Postgres projects, branches, roles and computes, run SQL and migrations on temporary branches, and configure Neon Auth, Data API and storage, through OAuth or an API key. Top strength OAuth 2.1 with read and write scopes, and grants fixed to one project, one Postgres role and chosen categories Top weakness 138 tools listed when no category or project is set |
||||||||||||
| 123 | StatsigAmplitude, Inc. · HTTP API | Product analytics | BB | 74.9 | 3.8 (4) | n/a | n/a | $150 / mo | OAuth or key | Hosted | ||
|
Statsig is a hosted platform for feature flags, experiments and product analytics, run by Amplitude, Inc. since May 2026. Agents reach it through the Console API, which has a public OpenAPI spec, and an official hosted MCP server. Top strength Hosted MCP server with 18 default tools and a discovery layer that replaced 93 tools on the V1 server Top weakness Console API errors carry only |
||||||||||||
| 124 | ElevenLabs Agents API + MCPElevenLabs · HTTP API | Voice agents | BB | 74.9 | 3.5 (2) | n/a | n/a | $22 / mo | OAuth or key | Hosted | ||
|
ElevenAgents (formerly Conversational AI) runs hosted voice agents as a pipeline of a fine-tuned ElevenLabs ASR model, an LLM of your choice or your own, ElevenLabs TTS and a proprietary turn-taking model. Top strength API keys scoped to endpoint groups, with per-key credit limits and service accounts Top weakness $0.08 a minute excludes LLM tokens and carrier minutes |
||||||||||||
| 125 | GitHub MCP ServerGitHub · MCP server | Code | BB | 74.9 | 4.0 (2) | n/a | n/a | Free · OSS | OAuth or key | Hosted and local | ||
|
GitHub's official MCP server (Go) exposing repositories, issues, pull requests, Actions, code security, discussions, gists, notifications, projects and more as toolsets. Top strength OAuth with scopes by default, fine-grained PATs and GitHub App tokens for headless runs, and per-call scope challenges since v1.11.0 Top weakness 92 tools and about 30,000 tokens with everything enabled; the default set alone is 45 tools |
||||||||||||
| 126 | CodexCodex Data Inc. · HTTP API | Data | BB | 74.9 | none | n/a | n/a | $0.001 / call | API key | Hosted | ||
|
Codex is a GraphQL API from Codex Data Inc. for on-chain crypto data, with token prices, OHLCV bars, trades, holders, wallet PnL, launchpads and prediction markets across 80+ networks, over HTTP, WebSocket subscriptions and webhooks. Top strength MPP on every query endpoint at $0.001 a query, so an agent can pay without signing up Top weakness The free plan needs a one-time $1 activation fee by card or 1 USDC |
||||||||||||
| 127 | Big ArrowFranz Enzenhofer · SDK + MCP | Human approval | BB | 74.8 | 3.3 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
bigarrow is an open-source macOS command-line tool, with a skill for Claude Code and Codex, that lets an agent point at any window with a click-through arrow and sign, or hand a person values and questions on a floating card. Top strength Drawing needs no macOS permission, and the overlay never takes keyboard focus, which integration tests on the real window server check Top weakness First commit 8 October 2026 and version 0.5.1, with flags removed or renamed between minor versions |
||||||||||||
| 128 | Grafana MCP ServerGrafana Labs · MCP server | Observability | BB | 74.8 | 3.0 (4) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Grafana Labs' open-source MCP server for Grafana. It runs locally or self-hosted and gives agents dashboards, datasource queries (Prometheus, Loki, Tempo, Pyroscope and others), alerting, incidents and OnCall on a self-managed Grafana or Grafana Cloud. Top strength All 79 default tools in 2.0.2 build typed JSON Schema inputs from Go parameter structs and set Top weakness The default set is 79 tools, and 119 with every category on, counted from the registration code in source |
||||||||||||
| 129 | AblyAbly Realtime Ltd · HTTP API | Webhooks | BB | 74.7 | 3.8 (4) | n/a | n/a | $29 / mo | API key | Hosted | ||
|
Hosted realtime messaging from Ably Realtime Ltd in London. Clients publish and subscribe on channels over WebSocket, SSE or MQTT, with a REST API, presence, message history, outbound and inbound webhooks, and AMQP queues. Top strength API keys and tokens carry per-channel capabilities (publish, subscribe, history and 16 others), and tokens can be revoked by client, channel or revocation key Top weakness No official MCP server. The Ably CLI's built-in one was removed in v0.17.0 on 8 March 2026 |
||||||||||||
| 130 | Pulumi ESCPulumi Corporation · HTTP API | Secrets | BB | 74.7 | 3.3 (4) | n/a | n/a | $0.01 / 1k req | OAuth or key | Hosted | ||
|
Pulumi ESC is the secrets and configuration service in Pulumi Cloud. Environments hold static secrets, pull from other vaults and issue short-lived cloud credentials over OIDC, read through the Pulumi CLI, a REST API and four SDKs. Top strength The Pulumi CLI creates a free ephemeral account for an agent with no signup, with write access for 72 hours and 30 days to claim it Top weakness Audit logs, custom roles, team tokens, approvals and customer-managed keys need Pro ($400 a month) or Enterprise |
||||||||||||
| 131 | Deepgram Voice Agent APIDeepgram · HTTP API | Voice agents | BB | 74.7 | 3.0 (2) | n/a | n/a | Pay per use | API key | Hosted and local | ||
|
One WebSocket that runs Deepgram STT (Flux or Nova-3), a managed or bring-your-own LLM and Deepgram or third-party TTS, with turn-taking, barge-in and function calling. Top strength $0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card Top weakness No phone numbers or SIP, so you bridge Twilio or another carrier yourself |
||||||||||||
| 132 | Scalekit AgentKitScalekit · HTTP API | Agent auth | BB | 74.7 | 2.5 (2) | n/a | n/a | $99 / mo | OAuth or key | Hosted | ||
|
Authentication and integration platform for agents, with per-user account connections, scoped MCP servers and managed tool calls. Top strength 600+ connectors, including remote MCP servers over OAuth 2.1 with DCR Top weakness No published rate-limit figure and no idempotency keys for Scalekit's own API |
||||||||||||
| 133 | WooCommerce API + MCPWooCommerce (Automattic) · HTTP API | Commerce | BB | 74.7 | 3.5 (2) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Open-source commerce plugin for WordPress that you host yourself. Top strength Free GPL software with no platform fee or revenue share Top weakness Uptime, speed and security depend on each store's host and plugins. No vendor status page |
||||||||||||
| 134 | GeocodioDotsquare LLC · HTTP API | Maps | BB | 74.7 | none | n/a | n/a | $1 / 1k req | API key | Local | ||
|
Geocodio is a hosted geocoding API from Dotsquare LLC for addresses in the US, Canada, Mexico, the UK, Australia and New Zealand. It does forward, reverse and batch geocoding, distance matrices and census, district and timezone data appends. Top strength llms.txt and AGENTS.md cover billing arithmetic, retry rules, idempotency on the client and when not to use the API Top weakness Covers only the US, Canada, Mexico, the UK, Australia and New Zealand, and UK needs a Flex or Unlimited plan |
||||||||||||
| 135 | NocoDBNocoDB Inc · HTTP API | Spreadsheets | BB | 74.6 | 3.5 (4) | n/a | n/a | $12 / seat-mo | OAuth or key | Hosted | ||
|
NocoDB is a database of typed records in bases, tables and views, run on NocoDB Cloud or self-hosted. Agents reach it through a REST API and a built-in MCP server, using scoped API tokens or OAuth. Top strength Fine-grained API tokens carry eight permission categories at Read or Read and write, a list of bases, an expiry and an on-off switch Top weakness 5 requests a second per user on every plan, shared by all of that user's tokens, with a 30-second block after a 429 |
||||||||||||
| 136 | Nylas Notetaker APINylas · HTTP API | Meetings | BB | 74.6 | 3.8 (4) | n/a | n/a | $15 / mo | API key | Hosted | ||
|
Nylas Notetaker is a meeting bot API that joins Google Meet, Microsoft Teams and Zoom calls, then returns a recording, a speaker-labelled transcript, a summary and action items. It works from a meeting link or a connected calendar. Top strength
Top weakness Invite requests accept no idempotency key, and every request schedules a new bot. Deduplication covers only Notetakers with a future |
||||||||||||
| 137 | SeleniumSelenium project (Software Freedom Conservancy) · SDK + MCP | Browser | BB | 74.6 | 3.8 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
Selenium is the open-source browser automation project behind the W3C WebDriver standard, with official bindings for Java, Python, C#, Ruby and JavaScript and a self-hosted Grid server that runs browsers on other machines. Top strength Official bindings for Java, Python, C#, Ruby and JavaScript, released together, 4.52.0 on 29 October 2026 Top weakness No MCP server from the project. The docs point to community servers and say they are third-party |
||||||||||||
| 138 | Amazon SNSAmazon Web Services · HTTP API | Notifications | BB | 74.5 | 3.5 (4) | n/a | n/a | $0.0005 / 1k req | OAuth or key | Hosted | ||
|
Amazon SNS is AWS's publish and subscribe messaging service. A message published to a topic, or directly to a device or phone number, goes out as mobile push, SMS, plain-text email, HTTPS calls or to SQS queues and Lambda functions. Top strength IAM identity policies and topic resource policies per action and topic, temporary credentials, and an Top weakness No idempotency token on |
||||||||||||
| 139 | Google Cloud Model ArmorGoogle Cloud · HTTP API | Guardrails | BB | 74.4 | 3.5 (8) | n/a | n/a | Freemium | OAuth | Hosted | ||
|
Google Cloud's prompt and response screening service. Top strength 2 million free tokens a month, then $0.10 per million Top weakness OAuth only, and a template must exist in the same location as the endpoint before the first call |
||||||||||||
| 140 | Telnyx Voice API + MCPTelnyx · HTTP API | Calling | BB | 74.4 | 3.5 (8) | n/a | n/a | $1 / mo | OAuth or key | Hosted and local | ||
|
Carrier-owned Voice API (Call Control and TeXML) for calls, numbers, websocket media streaming, recording and transfers on Telnyx's own network. Top strength About $0.007 a minute all-in for US outbound ($0.002 Voice API plus $0.005 termination) Top weakness x402 and MPP only top up credit, they don't pay per call, and x402 sits behind a per-account feature flag |
||||||||||||
| 141 | Firebase Cloud MessagingGoogle · HTTP API | Notifications | BB | 74.4 | 3.5 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
Google's push messaging service for Android, Apple and web apps. A server sends notification or data messages to devices, topics or conditions through the HTTP v1 API or the Firebase Admin SDKs. Top strength No charge for sending on either Firebase plan, and no billing account needed (https://firebase.google.com/pricing) Top weakness Push transport only. No in-app feed, email, SMS, user preferences, digests or templates |
||||||||||||
| 142 | GraphicleKarLex AI, Inc. · MCP server | Memory | BB | 74.4 | 3.8 (4) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Graphicle is an open-source Rust program that builds a code graph of a repository and keeps its documents, reviewed decisions and past coding-agent sessions, served to Claude Code, Codex, Cursor and other MCP clients as cited excerpts. Top strength 25 MCP tools with closed JSON Schema inputs, enums and limits, readOnlyHint on every read tool, and a five-tool essentials set Top weakness Version 0.1.10, about two weeks old, with stored-data changes shipped in patch releases |
||||||||||||
| 143 | PuppeteerGoogle · SDK + MCP | Browser | BB | 74.4 | 3.3 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
Puppeteer is Google's open-source Node.js library for controlling Chrome and Firefox over the DevTools Protocol and WebDriver BiDi. An agent writes and runs scripts that navigate, click, type, read pages and take screenshots. Top strength Twelve releases from 25.5.0 on 4 August to 25.16.0 on 22 October 2026, each with a changelog generated by release-please Top weakness No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project |
||||||||||||
| 144 | Context7Upstash · MCP server | Code | BB | 74.4 | 3.0 (2) | n/a | n/a | $5 / 1k calls | OAuth or key | Hosted and local | ||
|
Serves up-to-date, version-specific library documentation and code examples into agent prompts via two tools (resolve-library-id, query-docs). Top strength Two tools, both annotated Top weakness The |
||||||||||||
| 145 | SpiderSpider (BAGELMEN LLC) · HTTP API | Scrapers | BB | 74.3 | 3.3 (8) | n/a | n/a | $0.0005 / call x402 | OAuth or key | Hosted and local | ||
|
Hosted crawl, scrape, search, links and screenshot API built on the open-source Rust spider crate, plus a cloud browser and proxy pool. Top strength Keyless /scrape and x402 v2 on every core route, so an agent needs no account Top weakness No security.txt, disclosure policy, certification or prompt-injection guidance found |
||||||||||||
| 146 | Upstash QStashUpstash · HTTP API | Webhooks | BB | 74.3 | 3.3 (4) | n/a | n/a | $0.05 / GB | OAuth or key | Hosted | ||
|
Upstash QStash is a hosted HTTP message queue and scheduler. A caller publishes a request to its REST API, and QStash sends it to a public URL with retries, delays, cron schedules, FIFO queues and signed requests. Top strength Public OpenAPI 3.1 file with 43 operations for messages, queues, schedules, URL groups, the dead letter queue, logs and signing keys Top weakness One full-access token and one read-only token per region. No per-queue or per-destination scopes were found |
||||||||||||
| 147 | Langfuse API + MCPLangfuse (ClickHouse) · HTTP API | Evals | BB | 74.3 | 4.0 (2) | n/a | n/a | $29 / mo | API key | Hosted | ||
|
Open-source tracing, evaluation, prompt management and datasets for LLM apps and agents, built on OpenTelemetry. Top strength MIT core with no usage limits when self-hosted, and self-hosted telemetry documented with an off switch Top weakness 98 MCP tools load by default, writes included, and the MCP docs still leave read-only to a client allowlist |
||||||||||||
| 148 | AXLRUnderpass AI · Agent harness | Harnesses | BB | 74.3 | none | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Open-source Go execution engine for agentic work from Underpass AI. A console with work modes and approval cards, an mTLS HTTP, gRPC and MCP service, a JSON worker and a Go library, with KMP memory and MADE procedures over MCP. Top strength mTLS HTTP, gRPC and MCP service with four principal roles, Top weakness The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list |
||||||||||||
| 149 | Intercom API + MCPIntercom · HTTP API | Support | BB | 74.2 | 4.0 (2) | n/a | n/a | $29 / seat-mo | OAuth or key | Hosted | ||
|
Intercom's REST API (conversations, contacts, companies, tickets, notes, tags, articles, data attributes and webhooks) and its official hosted MCP server. Top strength Versioned OpenAPI per API version, 259 operations in 2.17, every one described Top weakness MCP can't reply, assign, snooze or close, those need the REST API |
||||||||||||
| 150 | LinqLinq App Inc. · HTTP API | Messaging | BB | 74.2 | none | n/a | n/a | $260 / mo | API key | Hosted and local | ||
|
Linq is a messaging API from Linq App Inc. for AI agents to send and receive iMessage, RCS and SMS from dedicated lines, with webhooks, SDKs, a CLI and an MCP server. WhatsApp is a separate API. Top strength OpenAPI 3.1 file for the Partner API, llms.txt and llms-full.txt per channel, and Markdown for every page Top weakness Plans are flat monthly prices (Pro from $260 a month), with Enterprise and its contractual SLA priced through sales |
||||||||||||
| open | Gemma 4 31B ITGoogle DeepMind · Open-weight model | Open weights | BB | 74.1 | 3.8 (4) | n/a | n/a | Free | None | Local | ||
|
Gemma 4 31B IT is Google DeepMind's open-weight dense multimodal model of 30.7B parameters, taking text and images with a 256K-token context, published on Hugging Face in BF16 with 4-bit QAT builds under Apache 2.0. Top strength Google's own 17.7 GB QAT Q4_0 GGUF fits a 24 GB GPU, and Ollama's gemma4:31b is 20 GB Top weakness No safety evaluation results published |
||||||||||||
| 151 | Nutrient DWS Processor APINutrient (PSPDFKit GmbH) · HTTP API | BB | 74.1 | 3.3 (4) | n/a | n/a | $75 / mo | OAuth or key | Hosted | |||
|
Hosted REST API from Nutrient (formerly PSPDFKit) that generates, converts, merges, OCRs, redacts, watermarks and signs PDF and Office documents. Agents call it with a Bearer key or through the hosted Nutrient MCP server. Top strength OpenAPI 3.1 document (17 operations in version 1.19.0, now 1.20.0), with llms.txt indexes and a Markdown twin of every guide Top weakness The local MCP server lost support on 14 October 2026, the day the change was announced |
||||||||||||
| 152 | LangSmith API + MCPLangChain · HTTP API | Evals | BB | 74.1 | 3.0 (2) | n/a | n/a | $39 / seat-mo | OAuth or key | Hosted | ||
|
LangChain's hosted tracing, evaluation, prompt hub and dataset platform, framework-agnostic with Python and TypeScript SDKs and OpenTelemetry ingest. Top strength Rate limits published per endpoint and per plan, with each kind of 429 explained Top weakness Five SDK advisories from February to June 2026, one listed as critical (arbitrary file read through |
||||||||||||
| 153 | Massive (formerly Polygon.io)Massive · HTTP API | Markets | BB | 74.1 | 3.5 (2) | n/a | n/a | $0.01 / call x402 | API key | Hosted | ||
|
US market data API for stocks, options, indices, forex, crypto and futures, from the consolidated tapes. Top strength 24 US stock routes over x402 at agent.massive.com, $0.01 each on Base, and only successful requests are charged Top weakness 14 partial incidents from 3 August to 1 November 2026, mostly stale or missing data on stock aggregates and quotes |
||||||||||||
| 154 | OpenHandsAll Hands AI · Agent harness | Harnesses | BB | 74.1 | 2.5 (2) | n/a | n/a | Freemium | OAuth or key | Local | ||
|
Open-source coding agent with a self-hosted web interface, local and remote execution, and scheduled or webhook-driven automation. Top strength A Docker container per conversation with Top weakness Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem |
||||||||||||
| 155 | DBHubBytebase · MCP server | Databases | BB | 74.1 | none | n/a | n/a | Free · OSS | None | Local | ||
|
DBHub is Bytebase's open-source MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite. It runs locally over stdio or HTTP with two default tools, SQL execution and schema search, plus read-only and row-limit guardrails. Top strength Two default tools, execute_sql and search_objects, at about 1.4k tokens Top weakness HTTP transport binds 0.0.0.0 with bearer authentication off unless configured |
||||||||||||
| 156 | Circle Wallets (Agent Wallets, Programmable Wallets)Circle · HTTP API | Wallets | BB | 74 | 3.1 (8) | n/a | n/a | 0.02% fee | OAuth or key | Hosted | ||
|
Circle's wallet APIs (developer-controlled, user-controlled and modular wallets) plus Agent Wallets, a USDC wallet an agent drives through the Circle CLI with per-transaction, daily, weekly and monthly caps and address allowlists. Top strength Agent Wallet caps per transaction, day, week and month plus recipient and contract allow and block lists, each change confirmed by email OTP Top weakness Developer-controlled wallets have no built-in spending caps; Compliance Engine rules need an application |
||||||||||||
| 157 | AgnoAgno Inc. · Agent framework | Frameworks | BB | 74 | 3.3 (4) | n/a | n/a | Free · OSS | API key | Library | ||
|
Open-source Python framework from Agno Inc. for building agents, teams and workflows, with the AgentOS runtime that serves them over a REST API and an MCP server. Formerly Phidata. Top strength Apache 2.0, with 27 stable releases tagged in the 90 days to 1 November 2026 and 3.1.12 on 29 October Top weakness Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent |
||||||||||||
| 158 | Azure Key VaultMicrosoft · HTTP API | Secrets | BB | 74 | 3.8 (4) | n/a | n/a | $0.003 / 1k calls | OAuth | Hosted | ||
|
Microsoft Azure's managed store for secrets, encryption keys and TLS certificates. Applications read secrets over a REST API or the Azure SDKs and CLI, signing in with Microsoft Entra ID and authorised by Azure role assignments. Top strength No API keys. Every call carries a Microsoft Entra ID bearer token, and managed identities remove stored credentials for workloads on Azure Top weakness No managed rotation for secrets. Key Vault raises a near-expiry event 30 days ahead and the owner's Azure Function does the rotation |
||||||||||||
| 159 | RestateRestate GmbH · Platform | Human approval | BB | 74 | 3.5 (4) | n/a | n/a | $75 / mo | API key | Local | ||
|
Durable execution runtime from Restate GmbH in Berlin, run as Restate Cloud, in the customer's own cloud account or self-hosted. Handlers pause on durable promises (awakeables and signals) and resume when a person answers over HTTP. Top strength One HTTP request resolves or rejects an awakeable, and the waiting handler resumes after restarts or redeployment Top weakness No reviewer inbox, Slack app or email. The approval request and the reply endpoint are the builder's code |
||||||||||||
| 160 | OpenAI Moderation APIOpenAI · HTTP API | Guardrails | BB | 74 | 4.0 (2) | n/a | n/a | Free | API key | Hosted | ||
|
Free classifier endpoint that scores text and images against 13 harm categories (harassment, hate, illicit, self-harm, sexual, violence and their sub-types) and returns a flagged boolean plus per-category scores. Top strength Free, on any OpenAI project key Top weakness No prompt-injection, jailbreak or PII detection |
||||||||||||
| 161 | Yield.xyz MCP serverOmni Ltd. (Yield.xyz) · MCP server | Wallets | BB | 74 | none | n/a | n/a | $0.001 / call x402 | OAuth or key | Hosted | ||
|
Yield.xyz's MCP server has 22 tools to find and track more than 4,000 staking, lending, vault and real-world-asset yields across 85 networks and build unsigned transactions. Keyless use is metered, with x402 per call over quota. Top strength x402 per call once the free quota runs out, with machine-readable pricing Top weakness A key can be sent as a query parameter |
||||||||||||
| 162 | Respan API + MCPRespan (formerly Keywords AI) · HTTP API | Evals | BB | 73.9 | 2.5 (2) | n/a | n/a | $199 / mo | OAuth or key | Hosted | ||
|
Hosted tracing, evals, prompt management and an LLM gateway to 250+ models, from the company formerly called Keywords AI. Top strength API keys with Read, Write, Gateway and Admin scopes, expiry and spend caps, bound to one project Top weakness Security fixes on 30 July, 28 August and 19 October 2026 disclosed only as one-line changelog entries |
||||||||||||
| 163 | LaunchDarklyCatamorphic, Co. (dba LaunchDarkly) · HTTP API | Product analytics | BB | 73.8 | 3.5 (4) | n/a | n/a | $10 / mo | OAuth or key | Hosted and local | ||
|
LaunchDarkly is a hosted feature flag and experimentation platform from Catamorphic, Co., with observability and AI configuration products. Agents reach it through an official hosted MCP server with OAuth and a REST API with a public OpenAPI spec. Top strength Public OpenAPI 3.0.3 spec with 401 operations, 399 of them described, with 1,853 examples and 429 documented on 287 operations Top weakness The hosted MCP server lists 141 tools, and no tool filter for it was found in the reviewed documentation |
||||||||||||
| 164 | Opik API + MCPComet · HTTP API | Evals | BB | 73.8 | 3.5 (4) | n/a | n/a | $19 / mo | OAuth or key | Hosted and local | ||
|
Opik is Comet's open-source platform for tracing, evaluating and optimising LLM apps and agents, under Apache-2.0. It runs self-hosted or on Comet's Opik Cloud, with a REST API, Python and TypeScript SDKs and a hosted MCP server. Top strength Five MCP tools carry readOnlyHint and destructiveHint, Top weakness No read-only mode or per-project scope for the MCP server, and the OAuth metadata advertises no scopes |
||||||||||||
| 165 | LlamaIndex FrameworkLlamaIndex · Agent framework | Frameworks | BB | 73.8 | none | n/a | n/a | Free · OSS | None | Library | ||
|
The LlamaIndex Framework is LlamaIndex's open-source Python toolkit for retrieval and agents, with FunctionAgent, ReActAgent and CodeActAgent, multi-agent AgentWorkflow, event-driven Workflows, MCP tools and hundreds of integration packages. Top strength FunctionAgent, ReActAgent, CodeActAgent and multi-agent AgentWorkflow over one Workflows engine Top weakness Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes |
||||||||||||
| 166 | 1Password service accounts, SDKs and Environments MCP1Password · Platform | Secrets | BB | 73.7 | 3.5 (2) | n/a | n/a | $8.99 / seat-mo | OAuth or key | Local | ||
|
Password manager with a developer layer for agents. Top strength Service accounts scoped per vault to read, write or share, with an optional expiry and permissions that can't be changed after creation Top weakness Teams, Families and Individual get 1,000 service account reads an hour per token, and the 429 carries no Retry-After |
||||||||||||
| 167 | Terraform MCP ServerHashiCorp (IBM) · MCP server | Infra | BB | 73.7 | 3.0 (2) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
HashiCorp's official MCP server for Terraform and its registry. Top strength Nine registry tools load by default and need no credentials Top weakness Workspace updates, variable writes, team membership and access grants run without the operations flag |
||||||||||||
| 168 | Drex 1.5Nace AI, Inc. (Nace.AI) · Model API | Decisions | BB | 73.6 | 3.5 (4) | n/a | n/a | Freemium | API key | Hosted | ||
|
Drex 1.5 is Nace.AI's decision model. It returns a probability for each option in typed yes or no, choice and score questions. Hosted at console.nace.ai, with open weights under the Nace AI Open RAIL-M licence. Top strength Public OpenAPI 3.1 document with POST /v1/systemone, /v1/decisions and GET /v1/models, plus llms.txt and a reference for limits and errors. Top weakness drex-v1.0 was retired on 21 October 2026, 27 days after release, and its requests now go to Drex Max at Max's limits and price, with no notice period published. |
||||||||||||
| 169 | FinchProfound Platform Inc. (dba Finch) · HTTP API | Payroll | BB | 73.6 | 3.0 (4) | n/a | n/a | Paid | OAuth | Hosted and local | ||
|
Finch is a unified API for reading an employer's existing HR and payroll system, run by Profound Platform Inc. in San Francisco. Applications read directory, employment and pay data from 250+ systems and write payroll deductions. Top strength One OpenAPI 3.1 file covers 55 operations, and llms.txt indexes the documentation with every page served as Markdown Top weakness Finch cannot create, preview or approve a payroll. Writes are limited to deductions and contributions, on Pro and Premier plans |
||||||||||||
| 170 | OpenAI Realtime APIOpenAI · HTTP API | Voice agents | BB | 73.6 | 3.3 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
OpenAI's Realtime API runs spoken conversations with speech-to-speech models such as `gpt-realtime-2.1`. Clients connect over WebRTC, WebSocket or SIP, and sessions support interruptions, function calling and remote MCP tools. Top strength The OpenAPI 3.1 file in Top weakness Realtime was degraded in two API-wide incidents, for an hour on 17 September and for 5 hours 21 minutes on 29 September 2026. |
||||||||||||
| open | Qwen3-Embedding-4BAlibaba (Qwen team) · Open-weight model | Embeddings | BB | 73.6 | 3.5 (4) | n/a | n/a | Free | None | Local | ||
|
Qwen3-Embedding-4B is Alibaba's open-weight text embedding model built on Qwen3-4B-Base, returning vectors of up to 2,560 dimensions for retrieval, code search and clustering in over 100 languages, under Apache 2.0. Top strength About 3 GB of memory for Alibaba's own Q4_K_M GGUF, with five more precisions up to F16 Top weakness No change to the files or reference code since August 2025, and no reply from Qwen to any of its 16 questions |
||||||||||||
| 171 | LangGraphLangChain · Agent framework | Frameworks | BB | 73.6 | 3.5 (2) | n/a | n/a | Free · OSS | None | Library | ||
|
Low-level runtime for long-running, stateful agent graphs with checkpointed persistence, human-in-the-loop, memory and streaming. Top strength Checkpointed persistence, so runs survive restarts and resume where they stopped Top weakness No MCP client of its own. LangChain's langchain.mcp is in beta |
||||||||||||
| 172 | OneSignalOneSignal · HTTP API | Notifications | BB | 73.6 | 3.5 (2) | n/a | n/a | $19 / mo | OAuth or key | Hosted | ||
|
Messaging platform that sends mobile and web push through its own service and adds email, SMS, RCS, in-app messages, Live Activities and journeys. Top strength Runs push delivery itself, so there's no separate push provider to wire up Top weakness Four partial incidents on the API and SDK endpoints between 18 September and 15 October 2026, the longest about 24 hours of incomplete reads for some apps |
||||||||||||
| spec | Universal Commerce Protocol (UCP)UCP Authors (Google, Shopify and co-developers) · Payment protocol | Checkout | BB | 73.6 | none | n/a | n/a | Free · OSS | OAuth | Specification | ||
|
The Universal Commerce Protocol (UCP) is an open specification, co-developed by Google, Shopify and other retailers and platforms, for agents to discover a business's capabilities and run catalogue, cart, checkout, identity linking and order flows over REST, MCP or A2A. Top strength Machine-readable contracts for every transport, OpenAPI, OpenRPC and JSON Schema 2020-12 Top weakness No release since v2026-08-25, though main changes most days |
||||||||||||
| 173 | SvixSvix Inc. · HTTP API | Webhooks | BB | 73.5 | 3.5 (4) | n/a | n/a | $20 / mo | API key | Hosted | ||
|
Svix is a webhook sending service with a hosted REST API and an MIT-licensed server. One call creates a message, and Svix signs it, sends it to each subscribed endpoint, retries failures and logs every attempt. Top strength OpenAPI 3.1 spec with 141 operations, each described, and code samples on 140 of them Top weakness An API key can make any API call for its environment. No read-only or scoped API key was found in the reviewed documentation |
||||||||||||
| 174 | Kraken APIPayward, Inc. · HTTP API | Exchanges | BB | 73.5 | none | n/a | n/a | 0.4% fee | OAuth or key | Local | ||
|
Kraken's exchange APIs cover spot, tokenised US stocks, forex and futures over REST, WebSocket and FIX, with rate limits by client tier, a self-service futures demo and kraken-cli, an open-source CLI whose kraken-mcp binary is a local MCP server. Top strength Official local MCP server with 152 typed tools in services, destructive_hint on dangerous tools and an elicitation approval before each unless disabled Top weakness No self-service spot sandbox; the spot UAT environment is on request through an account manager, and paper trading lives in the CLI |
||||||||||||
| 175 | AgentMail API + MCPAgentMail · HTTP API | Inboxes | BB | 73.4 | 3.1 (8) | n/a | n/a | $2 / call x402 | OAuth or key | Hosted and local | ||
|
Email inboxes for agents over REST. Top strength Inbox creation, threads, drafts, labels and per-inbox calendars built for agents, with Top weakness Email sending was down for 8 hours 7 minutes on 19 August 2026 |
||||||||||||
| 176 | Google Cloud Document AIGoogle Cloud · HTTP API | Documents | BB | 73.4 | 3.5 (4) | n/a | n/a | $1.50 / 1k pages | OAuth | Local | ||
|
Google Cloud's service for OCR, layout parsing, chunking, form and table extraction, classification and splitting of documents. Work runs through processors created per project and location. Access is a REST and gRPC API with client libraries in eight languages. Top strength Discovery document for v1 (revision 20261026) with 42 methods and 326 schemas, and descriptions on 952 of 966 properties Top weakness An online request reads at most 15 pages (30 with |
||||||||||||
| 177 | Privy Wallets (server wallets, agent wallets, policy engine)Privy (Stripe) · HTTP API | Wallets | BB | 73.4 | 3.5 (2) | n/a | n/a | $299 / mo | OAuth or key | Hosted | ||
|
Privy's wallet API for apps and AI agents, with server wallets and a policy engine that limits what each wallet can sign. Owned by Stripe since June 2025. Top strength Default-deny policies with DENY precedence on recipients, values, contracts, calldata, typed data and time windows, enforced in AWS Nitro Enclaves Top weakness Database problems caused outages across API endpoints for 71 minutes on 18 September 2026, one of 13 incidents since 3 August |
||||||||||||
| 178 | ImpeccableRenaissance Geek, Inc. · SDK + MCP | Design | BB | 73.4 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Impeccable is an open-source design skill for coding agents, with 24 commands for critique, audit and refinement, and a detector of 62 deterministic UI anti-pattern rules that runs as a CLI over files, folders or URLs. Top strength
Top weakness No JSON Schema for the findings; their shape is defined in a 610 KB contract document |
||||||||||||
| 179 | BrowserbaseBrowserbase · HTTP API | Browser | BB | 73.3 | 3.4 (8) | n/a | n/a | $0.12 / browser-hr x402 | API key | Hosted | ||
|
Hosted headless browsers for agents over CDP, plus Fetch and Search APIs and the Stagehand framework. Top strength x402 sessions at x402.browserbase.com with no account, $0.12 an hour, unused minutes refunded Top weakness The hosted MCP setup page passes the API key as |
||||||||||||
| 180 | MailerSendMailerSend, Inc. · HTTP API | BB | 73.3 | 2.5 (4) | n/a | n/a | $7 / mo | OAuth or key | Hosted | |||
|
Transactional email service from MailerSend, Inc. with a REST API, SMTP relay, templates, inbound routing, webhooks and analytics, plus SMS and WhatsApp sending. Agents reach it with a scoped API token or through a hosted MCP server. Top strength API tokens take any of 30 scopes, read or full by area, and can be limited to one sending domain Top weakness No idempotency key documented for POST /v1/email or the bulk endpoint |
||||||||||||
| 181 | Vercel ConnectVercel · HTTP API | Agent auth | BB | 73.3 | 3.5 (4) | n/a | n/a | $3 / 1k req | OAuth or key | Hosted | ||
|
Vercel Connect is a credential broker for apps and agents. Code asks it for a short-lived, scoped token for Slack, GitHub, Microsoft, Linear, Snowflake or any OAuth, API-key or MCP service, as the app or for a user. Top strength Refresh tokens stay on Vercel's infrastructure. Code receives only short-lived access tokens, as the app or for a named user Top weakness Vercel's SLA says it does not apply to the APIs or CLI, so token requests carry no uptime commitment |
||||||||||||
| 182 | Zoho CRMZoho · HTTP API | CRM | BB | 73.3 | 3.3 (4) | n/a | n/a | $14 / seat-mo | OAuth | Local | ||
|
Zoho CRM is a hosted sales CRM from Zoho. Agents reach it through the REST API v8, with record, search, query, bulk and notification endpoints behind OAuth 2.0, or through four pre-built remote MCP servers. Top strength OpenAPI 3.1 files for 103 resources and 644 operations are public on GitHub, with a Markdown page per operation Top weakness The documented refresh and revoke calls put the refresh token and client secret in the URL query string |
||||||||||||
| 183 | dYdXdYdX Trading Inc. · HTTP API | Exchanges | BB | 73.3 | none | n/a | n/a | 0.05% fee | OAuth or key | Local | ||
|
dYdX is a perpetuals exchange on its own Cosmos chain. Agents read markets and accounts from the indexer REST and WebSocket API at indexer.dydx.trade and place orders as signed chain transactions through the official TypeScript, Python and Rust clients. Top strength Permissioned keys limit a delegated key to chosen message types, subaccounts and markets, exclude withdrawals and transfers, and are removed with Top weakness No official MCP server; the one registry entry is a third party's analytics server |
||||||||||||
| 184 | Google Forms APIGoogle · HTTP API | Forms | BB | 73.2 | 2.5 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
REST API from Google for creating and editing Google Forms forms and quizzes, reading responses and quiz grades, and subscribing to change notifications through Cloud Pub/Sub. Access is by OAuth 2.0. Top strength Separate read-only scopes for form structure (forms.body.readonly) and responses (forms.responses.readonly), plus the per-file drive.file scope Top weakness Push notifications go only to a Cloud Pub/Sub topic in the caller's project, which needs Cloud billing, and they carry no form or response data |
||||||||||||
| 185 | LokaliseLokalise, Inc. · HTTP API | Translation | BB | 73.2 | 3.0 (4) | n/a | n/a | $149 / mo | OAuth or key | Hosted | ||
|
Lokalise is a hosted translation management system for software strings, documents and marketing content. Agents reach it through a REST API, the `lokalise2` CLI, SDKs in four languages and a hosted MCP server in beta. Top strength Three public OpenAPI 3.0.3 files, llms.txt with 182 reference links and a Markdown twin of every reference page Top weakness The Master Service Agreement forbids using the service for benchmarking or competitive analysis |
||||||||||||
| 186 | Azure TranslatorMicrosoft · HTTP API | Translation | BB | 73.2 | 3.5 (2) | n/a | n/a | $10 / mo | OAuth or key | Hosted | ||
|
Microsoft's translation API, now part of Foundry Tools. Top strength $10 per million characters pay as you go, 2 million free a month on F0, commitment overage down to $5.50 Top weakness The 2026-06-06 schema breaks v3.0 clients and drops BreakSentence and dictionary lookups from the spec |
||||||||||||
| 187 | E2BE2B · HTTP API | Sandboxes | BB | 73.2 | 3.0 (2) | n/a | n/a | $0.0504 / vCPU-hr | API key | Hosted | ||
|
Firecracker microVM sandboxes for agent code, driven from Python and JavaScript SDKs, a CLI or a REST API. Top strength Firecracker microVM with its own kernel per sandbox Top weakness Minor SDK releases 2.53.0, 2.56.0 and 2.62.0 (October 2026) shipped changes marked breaking, with no earlier notice |
||||||||||||
| 188 | NVIDIA NeMo GuardrailsNVIDIA · Agent framework | Guardrails | BB | 73.2 | 3.0 (2) | n/a | n/a | Free · OSS | None | Library | ||
|
Open-source Python toolkit that runs input, output, retrieval, dialogue and tool rails around any LLM. Top strength Apache-2.0, 7,200 stars and nine releases between 9 October 2025 and 16 September 2026 Top weakness Usage telemetry and a heartbeat every 10 minutes to NVIDIA by default |
||||||||||||
| 189 | AsanaAsana, Inc. · HTTP API | Projects | BB | 73.1 | 3.8 (4) | n/a | n/a | $10.99 / seat-mo | OAuth or key | Hosted | ||
|
Asana is a hosted work management product for tasks, projects, portfolios and goals. Agents reach it through a REST API with a public OpenAPI spec, or through the vendor's hosted MCP server. Top strength Public OpenAPI 3.0 spec with 271 described operations, rebuilt several times a week, plus llms.txt and Markdown copies of every docs page Top weakness On 21 October 2026 every Asana service, the API included, was unavailable in all regions for about 30 minutes, after partial API outages on 31 August and 30 September |
||||||||||||
| 190 | EasyshipEasyship Inc. · HTTP API | Shipping | BB | 73.1 | 3.5 (4) | n/a | n/a | $29 / mo | OAuth or key | Hosted and local | ||
|
Multi-carrier shipping platform from Easyship. Its public API and hosted MCP server quote courier rates, create shipments, buy labels, validate addresses, track parcels and book pickups across what Easyship says are 550+ courier services. Top strength Tokens carry per-resource read and write scopes, with separate sandbox (sand_) and production (prod_) tokens Top weakness No idempotency keys in the 132-operation spec, and no Retry-After or backoff guidance for 429 |
||||||||||||
| 191 | Merge Agent HandlerMerge · MCP server | Tool access | BB | 73.1 | 3.3 (4) | n/a | n/a | $1000 / mo | OAuth or key | Hosted | ||
|
Merge Agent Handler is a hosted MCP server from Merge API, Inc. that gives AI agents tools across more than 190 third-party connectors, with per-user credentials, tool packs, a security gateway and logs of every call. Top strength Access keys can be limited to named Registered Users and Tool Packs and to the Top weakness No rate limit figures are published. The docs say only that MCP tool calls are limited per Registered User and per organisation, by the minute |
||||||||||||
| 192 | RemoteRemote Technology, Inc. · HTTP API | HR | BB | 73.1 | 3.0 (4) | n/a | n/a | $29 / seat-mo | OAuth or key | Hosted | ||
|
Remote is a global employment platform covering employer of record, payroll, contractors and HR records. Its REST API, hosted MCP server and CLI let an agent read and update employments, time off, timesheets, expenses, onboarding and documents. Top strength OpenAPI 3.0 document with 308 operations and 116 webhook events, plus llms.txt and a Markdown copy of every docs page Top weakness The REST API changelog link in the docs redirects to a ReadMe dashboard login, so no public dated record of API changes was read |
||||||||||||
| 193 | SteelNen Labs, Inc. · HTTP API | Browser | BB | 73.1 | 2.0 (4) | n/a | n/a | $0.01 / call x402 | API key | Hosted and local | ||
|
Steel runs cloud browser sessions for AI agents, controlled through a REST API, a CDP WebSocket, SDKs, a CLI and an official MCP server. Its browser runtime, steel-browser, is open source and can be self-hosted. Top strength OpenAPI 3.0.3 document with 75 operations, llms.txt and a Markdown twin of every docs page Top weakness Two incidents of more than an hour hit session creation in the 90 days to 1 November 2026 (23 August, 1 October), per the status history read on 8 October |
||||||||||||
| 194 | Bandwidth Messaging API + MCPBandwidth · HTTP API | Messaging | BB | 73.1 | 3.5 (2) | n/a | n/a | Paid | OAuth | Hosted and local | ||
|
US carrier's messaging API for SMS, MMS and RCS over 10DLC, toll-free and short codes, with published US rates. Top strength 10DLC SMS $0.004, toll-free $0.007 and short code $0.008 a message, published Top weakness Production messaging accounts are onboarded by sales, and the Build trial can only text the verified number |
||||||||||||
| 195 | InngestInngest · Platform | Human approval | BB | 73.1 | 2.5 (2) | n/a | n/a | $99 / mo | OAuth or key | Hosted | ||
|
Durable execution platform for TypeScript, Python and Go, with event-driven workflows and support for human approval. Top strength Waits are durable and cost nothing while suspended, with runs up to 30 days on Free and 366 on Business Top weakness No reviewer inbox, Slack app or email, so the human side is your code |
||||||||||||
| 196 | NitrosendNitrosend Pty Ltd · HTTP API | Lifecycle marketing | BB | 73.1 | none | n/a | n/a | $20 / mo | OAuth or key | Hosted and local | ||
|
Nitrosend is an email marketing and transactional email platform built to be run by AI agents. Campaigns, automation flows, contacts, segments and approvals are driven through a remote MCP server, with a REST API, Node SDK and CLI. Top strength OpenAPI 3.1 with 258 described operations, llms.txt, llms-full.txt and Markdown twins of every docs page Top weakness status.nitrosend.com answered 526 on 6 November 2026, so no incident history could be read |
||||||||||||
| 197 | Spree CommerceVendo Connect Inc · HTTP API | Commerce | BB | 72.9 | 3.8 (4) | n/a | n/a | Freemium | OAuth or key | Local | ||
|
Spree Commerce is an open-source commerce platform on Ruby on Rails, maintained by Vendo Connect Inc. A self-hosted store runs a Store API for catalogue, cart and checkout, and an Admin API for back-office work. Top strength OpenAPI 3.0.3 files for the Store API (113 operations), Admin API (537) and Seller API (135), plus llms.txt and a Markdown copy of every docs page Top weakness Six GitHub security advisories between 8 January and 20 July 2026, four rated High, most of them access-control flaws on guest carts, orders and addresses |
||||||||||||
| 198 | ZepZep · HTTP API | Memory | BB | 72.9 | 4.0 (2) | n/a | n/a | $125 / mo | OAuth or key | Hosted | ||
|
Hosted context and memory service built on a temporal graph of facts, relationships and source episodes. Top strength Facts that new data invalidates keep the time they stopped being true Top weakness The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data |
||||||||||||
| 199 | MCP GatewayMikko Parkkola · MCP server | Tool access | BB | 72.9 | none | n/a | n/a | $500 / mo | OAuth or key | Local | ||
|
MCP Gateway is a self-hosted Rust binary that runs on the user's machine in front of their own MCP servers and REST APIs, unlike hosted app catalogues, and gives the agent a few search and invoke meta-tools. Top strength The agent sees 9 to 17 meta-tools, 11 in the default admin set, however many backends sit behind it; Code Mode cuts that to two Top weakness The project's own live run found the meta path used 1.2 to 16.1 per cent more input tokens and one extra turn on every task |
||||||||||||
| 200 | Netlify API + MCPNetlify, Inc. · HTTP API | Infra | BB | 72.9 | none | n/a | n/a | $9 / mo | OAuth or key | Hosted and local | ||
|
Netlify's platform for deploying and running web projects, reached through a REST API with a public OpenAPI spec, the netlify-cli command line tool and an official MCP server, hosted at netlify-mcp.netlify.app or run locally from npm. Top strength OpenAPI spec (Swagger 2.0, version 2.63.1) with 188 operations, llms.txt and a Markdown twin of every docs page Top weakness Personal access tokens and OAuth apps have no scopes, so a token reaches every team its owner belongs to |
||||||||||||
| 201 | YoutrustYoutrust SAS · HTTP API | E-signatures | BB | 72.9 | none | n/a | n/a | $116 / mo | OAuth or key | Hosted | ||
|
Youtrust, formerly Yousign, is a French electronic signature and digital trust service. Its Public API v3 creates signature requests with documents, signers and fields, activates and tracks them, runs identity and company checks, applies electronic seals and sends webhooks. Top strength OpenAPI 3.0.0 file with 178 operations, 282 enums and 1,307 examples, plus llms.txt and a Markdown twin of every page Top weakness No idempotency keys, and no Retry-After on the 429 |
||||||||||||
| 202 | xAI API (Grok)SpaceXSI (xAI) · Model API | Models | BB | 72.9 | none | n/a | n/a | from $1.25 / 1M in | API key | Hosted | ||
|
xAI's API for its Grok models (the docs now name the company SpaceXSI), with text, image, video and voice endpoints, server-side search and remote MCP tools, through an OpenAI-compatible REST API or gRPC. Top strength Grok 4.7 at $2/$6 per million tokens below 200K prompt tokens, with a 500K context and 20% off through the Batch API Top weakness API models outage of about 3 hours 40 minutes on 3 September 2026, and high error rates on grok-4.6 and grok-4.5 on 17 August |
||||||||||||
| 203 | AirtableFormagrid Inc (Airtable) · HTTP API | Spreadsheets | BB | 72.8 | 3.5 (4) | n/a | n/a | $20 / seat-mo | OAuth or key | Hosted | ||
|
Airtable is a hosted database of typed records organised in bases, tables and views. Agents reach it through a REST Web API and an official hosted MCP server, using personal access tokens or OAuth. Top strength Personal access tokens and OAuth grants are limited by scope and by base or workspace, and the legacy Top weakness 5 requests a second per base, and a 429 blocks further requests for 30 seconds |
||||||||||||
| 204 | Claude Agent SDKAnthropic · Agent framework | Frameworks | BB | 72.8 | 2.5 (4) | n/a | n/a | Free | API key | Library | ||
|
Runs the Claude Code agent as a library, with its loop, built-in tools, permissions, sessions, hooks and subagents. Top strength Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks Top weakness Claude models only, so a person has to set up a Claude API key or cloud account first |
||||||||||||
| 205 | DeciderMark Marosi (Mapika) · Model API | Decisions | BB | 72.8 | 3.3 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
Decider is a family of open-weight decision models by Mark Marosi (Mapika), from 0.8B to 35B parameters under Apache-2.0. It answers typed yes or no, choice and score questions with probabilities, and runs locally from the `decider-ai` Python package. Top strength Apache-2.0 code and weights, with the training code, data builders and per-version measurements in the repository Top weakness The local server has no authentication option. It binds to 127.0.0.1 since 1.7.1 |
||||||||||||
| 206 | Apideck Accounting API + MCPApideck · HTTP API | Accounting | BB | 72.8 | 3.5 (2) | n/a | n/a | $599 / mo | API key | Hosted and local | ||
|
Unified accounting API for invoices, bills, payments, journal entries and financial reports across platforms including QuickBooks, Xero and NetSuite. Top strength 62 accounting connectors, including European ledgers such as DATEV, Exact Online, Fortnox and Twinfield Top weakness No published rate limits of Apideck's own, only connector limits mirrored in headers |
||||||||||||
| 207 | Pipedream API + MCPPipedream (Workday) · HTTP API | Workflows | BB | 72.8 | 2.5 (2) | n/a | n/a | $150 / mo | OAuth or key | Hosted | ||
|
Code-first workflows in Node.js, Python, Go and Bash, plus Connect, an API and SDK that runs 10,000+ prebuilt actions across 3,000+ apps on behalf of your own users with managed OAuth. Top strength Managed OAuth per end user across 3,000+ apps, through API, SDK or MCP Top weakness Public product changelog's last entry is 1 October 2025 |
||||||||||||
| 208 | BoldSignSyncfusion, Inc. · HTTP API | E-signatures | BB | 72.8 | none | n/a | n/a | $30 / mo | OAuth or key | Hosted | ||
|
BoldSign is Syncfusion's electronic signature service. Its REST API sends documents for signature from files or templates, embeds signing and requesting in other products, manages templates, users and teams, and reports events by webhook, with a hosted MCP server. Top strength OpenAPI 3.0.4 file with 87 operations, llms.txt and a Markdown twin of every docs page Top weakness API keys carry every scope and the docs say that is not customisable; only OAuth apps get narrower scopes, and there is no Documents.Read scope |
||||||||||||
| 209 | Groq Speech-to-TextGroq · Model API | STT | BB | 72.6 | 3.5 (4) | n/a | n/a | Freemium | API key | Hosted | ||
|
Groq's hosted speech-to-text API. It runs OpenAI's Whisper Large v3 and Whisper Large v3 Turbo on OpenAI-compatible transcription and translation endpoints, for uploaded files or audio URLs, with a half-price batch mode. Top strength Published prices of $0.04 an audio hour for Whisper Large v3 Turbo and $0.111 for Whisper Large v3, with 50% off through the Batch API Top weakness No streaming or realtime endpoint and no diarisation in the reviewed documentation |
||||||||||||
| 210 | monday.commonday.com Ltd. · HTTP API | Projects | BB | 72.6 | 3.3 (4) | n/a | n/a | $9 / seat-mo | OAuth or key | Hosted | ||
|
monday.com is a hosted work management platform built on boards, items and columns. Agents reach it through a GraphQL API at api.monday.com/v2 and an official hosted MCP server, using personal API tokens or OAuth. Top strength Full GraphQL schema is public as SDL and JSON at api.monday.com/v2/get_schema, with a copy for each dated API version Top weakness Personal API tokens have no scopes. Each carries every permission its user has in the app |
||||||||||||
| 211 | OpenCodeAnomaly · Agent harness | Harnesses | BB | 72.6 | 2.0 (2) | n/a | n/a | $10 / mo | None | Local | ||
|
Open-source terminal coding agent from Anomaly Innovations, with a TUI, desktop app, IDE and ACP integration, and a headless HTTP server with an OpenAPI spec. Version 2, released in October 2026, is an opt-in upgrade. Top strength Runs with no key or account on free OpenCode Zen models Top weakness Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox |
||||||||||||
| 212 | fal music modelsfal (Features & Labels, Inc.) · Platform | Music | BB | 72.6 | 4.0 (2) | n/a | n/a | $0.04 / call | API key | Hosted | ||
|
fal hosts third-party music models behind one queue API and one key. Top strength Lyria, ElevenLabs, MiniMax, Mureka, Stable Audio and open-weights models behind one queue API Top weakness Billing units differ per model (per track, per second, per song, per minute rounded up) |
||||||||||||
| 213 | ClickHouse MCP ServerClickHouse · MCP server | Databases | BB | 72.5 | 3.3 (4) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
ClickHouse's open-source MCP server for ClickHouse databases. The owner runs it locally or self-hosted, and it gives agents SQL queries, database and table listing, and an optional embedded chDB engine. Queries are read-only by default. Top strength Read-only by default through ClickHouse's Top weakness
|
||||||||||||
| 214 | VespaVespa.ai AS · HTTP API | Retrieval | BB | 72.5 | 3.0 (4) | n/a | n/a | $0.05 / vCPU-hr | OAuth or key | Local | ||
|
Vespa is an open-source search engine from Vespa.ai AS for vector, text and hybrid retrieval with ranking, run self-hosted or on Vespa Cloud. Agents reach it through HTTP query and document APIs, the Vespa CLI and a Python client. Top strength Data-plane clients use mTLS certificates or tokens, each limited to Top weakness No OpenAPI file was found in the docs index. The APIs are described in reference pages only |
||||||||||||
| 215 | Wikimedia REST APIWikimedia Foundation · HTTP API | Data | BB | 72.5 | 4.0 (2) | n/a | n/a | Free | None | Hosted | ||
|
Keyless REST API for Wikipedia and the other Wikimedia projects, with page content, search and full revision history. Top strength Keyless reads in about 300 language editions with revision history since 2001 Top weakness api.wikimedia.org is being retired in stages through 2026 |
||||||||||||
| 216 | GraphifyGraphify Labs · MCP server | Code | BB | 72.5 | none | n/a | n/a | Free · OSS | None | Local | ||
|
Graphify is an open-source Python tool from Graphify Labs that turns a repository, plus its docs and media, into a knowledge graph a coding agent queries through a CLI, an installed assistant skill or a local ten-tool MCP server. Top strength Code graphs build offline with tree-sitter, with no embeddings and no model call, and no telemetry code was found in the source Top weakness Headless extraction sends docs to whichever cloud provider's key is set, Gemini first and Kimi in China second, unless |
||||||||||||
| 217 | Agent Development Kit (ADK)Google · Agent framework | Frameworks | BB | 72.4 | 3.0 (8) | n/a | n/a | Free · OSS | None | Library | ||
|
Google's code-first toolkit to build, evaluate and deploy agents in Python, TypeScript, Go, Java and Kotlin. Top strength Python, TypeScript, Go, Java and Kotlin, with Python 2.13.0 on 23 October and Java 1.13.0 on 21 October 2026 Top weakness Six CVEs in 2026, three of them critical, one in tool confirmation itself |
||||||||||||
| 218 | Amazon Bedrock AgentCore Code InterpreterAmazon Web Services · HTTP API | Sandboxes | BB | 72.4 | 3.3 (4) | n/a | n/a | $0.0895 / vCPU-hr | API key | Hosted | ||
|
Amazon Bedrock AgentCore Code Interpreter is AWS's managed sandbox for running agent-written Python, JavaScript and TypeScript. Each session is a dedicated microVM, reached through the AWS API, the AgentCore SDKs or an MCP server. Top strength Each session runs in a dedicated microVM, which AWS says is terminated and has its memory sanitised when the session ends Top weakness No pause, resume or snapshot. Session files are removed when the session ends, and persistence needs a customer-owned S3 Files or EFS mount inside a VPC |
||||||||||||
| 219 | Nebius AI CloudNebius · HTTP API | GPU compute | BB | 72.4 | 3.0 (4) | n/a | n/a | Pay per use | OAuth or key | Hosted and local | ||
|
Nebius AI Cloud rents NVIDIA GPU virtual machines and InfiniBand clusters, with managed Kubernetes, Slurm and Serverless AI jobs and endpoints for containers. Resources are managed through REST and gRPC APIs, a CLI, a Terraform provider and SDKs. Top strength OpenAPI 3.0.3 document at Top weakness The status page lists 27 incidents from 5 August to 31 October 2026, each limited to a region, service or group of nodes, among them about 21 hours of degradation in us-central1 |
||||||||||||
| 220 | Qwen CodeAlibaba (Qwen team) · Agent harness | Harnesses | BB | 72.4 | 2.8 (4) | n/a | n/a | Free · OSS | API key | Local | ||
|
Open-source coding agent from Alibaba's Qwen team for the terminal, with desktop, browser and editor interfaces. It runs Qwen, OpenAI, Anthropic and Gemini-compatible models or a local one, and runs headless with `qwen -p`. Top strength Apache-2.0, with a release most weeks (39 stable from 3 August to 1 November 2026) and CodeQL and a monthly scorecard in CI Top weakness The default approval mode is Auto, where an LLM classifier approves tool calls, and sandboxing and folder trust are both off by default |
||||||||||||
| 221 | LayaConvai Innovations · Model API | Decisions | BB | 72.4 | 2.5 (2) | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source decision engine from Convai Innovations, released under Apache-2.0. Top strength Apache-2.0 code and weights, installed with Top weakness Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning |
||||||||||||
| 222 | Merge Accounting APIMerge · HTTP API | Accounting | BB | 72.4 | 3.5 (2) | n/a | n/a | $650 / mo | API key | Hosted | ||
|
Unified accounting API for invoices, payments, expenses, journal entries and financial statements across platforms including QuickBooks, Xero and NetSuite. Top strength 12 accounting platforms behind one set of common models, with writes Top weakness Launch jumps from free to $650 a month at the fourth linked account |
||||||||||||
| open | Gemma 4 12B ITGoogle DeepMind · Open-weight model | Open weights | BB | 72.3 | 3.8 (4) | n/a | n/a | Free | None | Local | ||
|
Gemma 4 12B IT is Google DeepMind's open-weight instruction-tuned dense model, 11.95B parameters in an encoder-free design, taking text, images, video frames and audio with a 262,144-token context, published on Hugging Face under Apache 2.0. Top strength Plain Apache 2.0, no account or gate, safetensors and GGUF only with a checksum on every file Top weakness No safety evaluation figures published |
||||||||||||
| 223 | REAmorluto · MCP server | Code | BB | 72.3 | 2.8 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
REA (Reverse Engineer Anything) is an open-source MCP server and CLI that gives coding agents local reverse-engineering tools for native binaries through Hopper, Ghidra or IDA, plus JavaScript and Electron apps, .NET, Android, websites, network captures and process behaviour. Top strength MIT licence, one npm package, and setup that registers the server with 14 named agent clients Top weakness 229 tools are advertised at once, including those whose provider is not installed, with no toolsets or read-only subset |
||||||||||||
| 224 | WebflowWebflow, Inc. · HTTP API | CMS | BB | 72.3 | 3.3 (4) | n/a | n/a | $15 / mo | OAuth or key | Hosted | ||
|
Webflow is a hosted website builder with a built-in CMS. Agents reach it through the Data API v2 (collections, items, assets, pages, locales, publishing) or the official hosted MCP server, which wraps that API in 34 tools. Top strength Public OpenAPI 3.1 spec for Data API v2 with 140 operations, MIT, last synced on 2 September 2026, plus llms.txt and a Markdown copy of every docs page Top weakness The MCP server documents 34 tools (27 data, 3 Designer session, 4 utility), each with several actions, and a granted tool grants all its actions |
||||||||||||
| 225 | past.devRevo Inc. (doing business as Past Corp.) · HTTP API | Memory | BB | 72.3 | 3.0 (4) | n/a | n/a | $99 / mo | OAuth or key | Hosted | ||
|
past.dev is a hosted long-term memory API for AI agents. Applications send timestamped text and recall ranked, dated evidence as a named identity, with per-audience access, OAuth MCP servers and plugins for coding agents. Top strength Public OpenAPI 3.1 file covering 34 operations, plus llms.txt, Markdown for every page and a docs MCP server Top weakness The changelog says the API is unversioned and its paths may change, and breaking changes shipped in the weeks of 21 September and 19 October |
||||||||||||
| 226 | Cloudflare MCP ServersCloudflare · MCP server | Infra | BB | 72.3 | 3.0 (2) | n/a | n/a | Your plan | OAuth or key | Hosted | ||
|
A family of Cloudflare-hosted remote MCP servers. Top strength OAuth on every account server, with a Minimal default template and step-up authorisation for further scopes since 19 October 2026 Top weakness No per-call confirmation before destructive calls once a write scope is granted |
||||||||||||
| 227 | Gladia Speech-to-Text API + MCPGladia · Model API | STT | BB | 72.3 | 3.0 (2) | n/a | n/a | Freemium | API key | Hosted and local | ||
|
Speech-to-text API for live and recorded audio, with multilingual transcription and code switching. Top strength 100+ languages on Top weakness Self-serve audio is used for model training by default unless the account opts out |
||||||||||||
| 228 | VendureVendure (Elevantiq GmbH) · HTTP API | Commerce | BB | 72.3 | 3.0 (2) | n/a | n/a | Freemium | OAuth or key | Hosted | ||
|
Open-source headless commerce framework on TypeScript, NestJS and GraphQL that you self-host. Top strength Full cart, coupon, shipping and payment flow in the GraphQL Shop API, with ErrorResult types an agent can branch on Top weakness No vendor-hosted API. Vendure Cloud is in a closed beta for paid subscribers |
||||||||||||
| 229 | Qdrant API + MCPQdrant · HTTP API | Retrieval | BB | 72.2 | 3.6 (8) | n/a | n/a | Freemium | API key | Hosted and local | ||
|
Open-source vector database written in Rust, run yourself or on Qdrant Cloud. Top strength Database keys can be read-only, limited to chosen collections and expire after 90 days by default Top weakness The MCP server has 2 tools, can't manage collections, and last released on 10 December 2025 |
||||||||||||
| 230 | DeelDeel, Inc. · HTTP API | HR | BB | 72.2 | 2.8 (4) | n/a | n/a | $5 / seat-mo | OAuth or key | Hosted | ||
|
Deel is a global HR, payroll and employer-of-record platform. Its REST API and hosted MCP server let an agent read and update people records, time off, organisation structure, onboarding, contracts and compliance documents. Top strength Public OpenAPI 3.1 specs with 541 operations and 55 webhook events, plus llms.txt and a Markdown copy of every docs page Top weakness 5 requests a second shared by every token in an organisation, with no rate limit headers on REST responses per the rate limits page |
||||||||||||
| open | Gemma 4 26B A4B ITGoogle DeepMind · Open-weight model | Open weights | BB | 72.2 | 3.8 (4) | n/a | n/a | Free | None | Local | ||
|
Gemma 4 26B A4B IT is Google DeepMind's open-weight instruction-tuned mixture-of-experts model, 25.2B parameters with 3.8B active, taking text and images with a 262,144-token context, published on Hugging Face under Apache 2.0. Top strength Plain Apache 2.0, no account or gate, safetensors and GGUF only with a checksum on every file Top weakness No safety evaluation figures published |
||||||||||||
| 231 | ZeroClawZeroClaw Labs · Agent harness | Assistants | BB | 72.2 | 3.3 (4) | n/a | n/a | Free · OSS | None | Local | ||
|
Open-source personal AI assistant from ZeroClaw Labs, shipped as one Rust binary the owner runs. It answers on chat, email and voice channels, calls tools and MCP servers, and keeps memory in local SQLite. Top strength Supervised mode is the default. Tools outside an eleven-item read-only and fetch list prompt the owner, and an unanswered prompt is a denial after 120 seconds Top weakness The docs state that command execution is not audited. |
||||||||||||
| 232 | Zyte APIZyte Group Limited · HTTP API | Scrapers | BB | 72.2 | 3.8 (4) | n/a | n/a | $0.13 / 1k req | OAuth or key | Hosted | ||
|
Zyte API is a hosted web scraping API from Zyte Group Limited of Cork, Ireland. One endpoint returns a page's HTTP body, browser-rendered HTML, a screenshot or extracted structured data, with ban avoidance handled by the service. Top strength OpenAPI 3.0.3 contract for Top weakness Request price depends on the target site's tier, from $0.13 to $1.27 per 1,000 HTTP requests and $1.01 to $16.08 with a browser on pay-as-you-go |
||||||||||||
| 233 | fal video modelsfal (Features & Labels, Inc.) · Platform | Video | BB | 72.2 | 3.3 (4) | n/a | n/a | Pay per use | OAuth or key | Hosted | ||
|
fal hosts third-party and open-weights video models, including Seedance, Kling, Veo, MiniMax and Wan, behind one queue API, one key and a hosted MCP server. Top strength 152 text-to-video endpoints in the catalogue API on 1 November 2026, 121 active, plus image-to-video and video-to-video categories Top weakness Billing differs per model (per second by resolution, per second by audio, per 1,000 tokens), and Kling v3 Pro shows $0.14 on the pricing page against $0.112 or $0.168 on its model page |
||||||||||||
| 234 | Azure MCP ServerMicrosoft · MCP server | Infra | BB | 72.1 | 2.5 (2) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
Microsoft's official local MCP server for Azure (`@azure/mcp`, also on NuGet as Azure.Mcp). Top strength Entra ID through DefaultAzureCredential, so access follows RBAC and no secret sits in the MCP config Top weakness Prereleases renamed and removed tools with no notice period, and npm |
||||||||||||
| 235 | ValyuValyu · HTTP API | Search | BB | 72.1 | 4.5 (2) | n/a | n/a | $0.625 / 1k pages | OAuth or key | Hosted | ||
|
Search API that covers the web plus specialised sources (arXiv, PubMed, SEC filings, market data, patents, clinical trials, genomics). Top strength Web plus academic, financial, patent and life-science sources behind one search call Top weakness Per-plan rate limits are stated only in example responses, not in a table |
||||||||||||
| 236 | DigitalOcean Managed AgentsDigitalOcean, LLC · HTTP API | Sandboxes | BB | 72.1 | none | n/a | n/a | $0.044 / vCPU-hr | OAuth or key | Hosted | ||
|
DigitalOcean Managed Agents runs agent harnesses and arbitrary code in Firecracker microVM sandboxes with pause, resume, checkpoint and fork, through Harness Runtime, and brokers tool access through Action Gateway's managed MCP endpoint. Both are in public preview. Top strength 67 Harness Runtime operations in the API reference, generated from DigitalOcean's public OpenAPI description, with llms.txt and a Markdown copy of every docs page Top weakness Public preview only. The preview terms exclude SLAs, support obligations and data durability guarantees |
||||||||||||
| 237 | Murf TTS API + MCPMurf · Model API | TTS | BB | 72 | 3.5 (2) | n/a | n/a | Freemium | API key | Hosted and local | ||
|
Murf's API for generating speech from text. Top strength Falcon 2.1 costs 1 cent per 1,000 characters on pay as you go, with a $2 minimum purchase Top weakness Falcon 2.1 concurrency is 2 outside US-East on free and pay as you go, 5 on US-East |
||||||||||||
| 238 | fal image modelsfal (Features & Labels, Inc.) · Platform | Image | BB | 72 | 4.0 (2) | n/a | n/a | Pay per use | OAuth or key | Hosted | ||
|
Model platform hosting hundreds of third-party image models behind one key and one queue API. Top strength Hundreds of image models, including FLUX, Nano Banana, GPT Image, Seedream, Recraft and Ideogram, on one key Top weakness Billing units vary by model, per image, per megapixel or per token |
||||||||||||
| 239 | Axiom MCP ServerAxiom, Inc. · MCP server | Observability | BB | 72 | none | n/a | n/a | $25 / mo | OAuth | Hosted | ||
|
Axiom's hosted MCP server at mcp.axiom.co lets AI agents query logs, traces, events and metrics in an Axiom organisation with APL, read and manage dashboards, monitors and notifiers, and inspect the service map, over OAuth or a token header. Top strength
Top weakness The server is closed source and tool input schemas are only visible through an authenticated session |
||||||||||||
| 240 | letmeAnchor Terminal · HTTP API | Tool access | BB | 71.9 | 3.8 (8) | n/a | n/a | Free | None | Hosted | ||
|
letme (letme.dev) picks a tool for a job from Anchor Terminal's published grades by one published rule and says how to call it direct. Agents ask by job, capability or listing over HTTP or MCP, with no key. Top strength Keyless and free, with no account or card, so an agent can ask for a pick on its first request. Top weakness Calling through letme, the letme key and x402 top-ups are specified but not open on 11 November 2026. |
||||||||||||
| 241 | GPT-LiveOpenAI · HTTP API | Voice agents | BB | 71.9 | 3.5 (4) | n/a | n/a | Pay per use | API key | Hosted | ||
|
GPT-Live is OpenAI's full-duplex voice API (`gpt-live-1`), which listens while it speaks and delegates reasoning and tools to a Responses model, the Decisions API or the developer's own agent. Clients connect over WebRTC, WebSocket or SIP. Top strength The OpenAPI 3.1 file has seven Top weakness The Live component on status.openai.com has data only from 16 October 2026, so the five weeks after general availability have no readable history. |
||||||||||||
| 242 | DopplerDoppler · HTTP API | Secrets | BB | 71.9 | 3.0 (2) | n/a | n/a | $21 / seat-mo | OAuth or key | Hosted and local | ||
|
Hosted secrets manager organised by project, environment and config. Top strength Service tokens bound to one config, read-only by default, with --max-age expiry Top weakness Dynamic secrets and on-prem are Enterprise only, and Developer has no service accounts |
||||||||||||
Nothing matches these filters. or search the MCP registry.
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser and cover every page; without JavaScript, the pages below the table list every listing.
Browse by category
How the ranking works
Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.