Category · Work & business apps
Agent tool access: app actions and authentication for agents
Services that hand an agent ready-made actions across thousands of apps, with the OAuth connections and credentials handled for you. Compared on action coverage, how authorisation works per end user, what the agent sees in its context, logs and price per call. Workflow builders are compared separately.
Best agent tool access platforms, the shortlist66 head-to-head comparisons
Capability keys automation.apps · automation.auth · automation.actions · agent.tools · All tools
letme.dev/automation.apps picks the top-graded tool in this list and says how to call it direct (how letme works).
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 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 |
||||||||||||
| 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 |
||||||||||||
| 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 |
||||||||||||
| 239 | 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. |
||||||||||||
| 379 | OneOne Systems, Inc. · MCP server | Tool access | B | 68.3 | 3.0 (4) | n/a | n/a | $29 / mo | OAuth or key | Hosted and local | ||
|
One is a hosted MCP server and CLI from One Systems, Inc. (formerly Pica) that lets AI agents find and run actions in a user's connected apps, with credentials held by One and access scoped per connection. Top strength The remote server has three tools whatever the number of connections, and Top weakness The remote server's tools changed from four to three by 30 September 2026, and the site's changelog, last dated 13 July 2026, has no entry for it |
||||||||||||
| 406 | StackOneStackOne Technologies Limited · MCP server | Tool access | B | 67.9 | 3.0 (4) | n/a | n/a | $600 / mo | OAuth or key | Hosted | ||
|
StackOne is a hosted gateway from StackOne Technologies Limited that gives AI agents actions across more than 540 business apps over MCP, SDKs, A2A or HTTP, with managed authentication, per-user grants, policies and logs. Top strength The MCP server at Top weakness Session token URLs ( |
||||||||||||
| 411 | Unified.to MCP ServerUnified API Inc. · MCP server | Tool access | B | 67.8 | 2.5 (4) | n/a | n/a | $750 / mo | OAuth or key | Hosted | ||
|
Unified.to MCP Server is a hosted Streamable HTTP server from Unified API Inc. that turns one end-customer connection to a business app into MCP tools, on top of the vendor's unified API for CRM, HR, accounting and other categories. Top strength A credential-free preview of the HubSpot tool list returned 81 tools on 2 November 2026, each with a JSON Schema input and Top weakness A connection's data tools still need the workspace API key, which the docs say grants access to all connections and the whole account, or a non-expiring connection token |
||||||||||||
| 614 | SandBaseAXIOMCLOUD PTE. LTD. · Platform | Tool access | B | 63.6 | none | n/a | n/a | Pay per use | API key | Hosted and local | ||
|
SandBase is a hosted gateway where an agent searches a catalogue of third-party models and data APIs, reads each one's schema and price, and runs it from one prepaid balance, over HTTP, a remote MCP server or a CLI. Top strength Seven compact MCP tools; discovery, inspection, run status and balance are free, and Top weakness No published rate-limit numbers, |
||||||||||||
| 717 | Zapier MCP (agent actions)Zapier · MCP server | Tool access | C | 61.4 | 2.5 (2) | n/a | n/a | Your plan | OAuth or key | Hosted | ||
|
Hosted MCP server that lets agents discover and run actions across apps connected to the user's Zapier account. Top strength 16 meta-tools in agentic mode, or managed mode with only the actions you pick Top weakness Connection tokens are long-lived and the docs allow them in the URL query string |
||||||||||||
| 879 | MonidMonid, Inc. · HTTP API | Tool access | C | 57.2 | 3.3 (4) | n/a | n/a | $0.01 / call x402 | OAuth or key | Hosted | ||
|
Monid is a hosted gateway where an AI agent searches a catalogue of third-party data and media endpoints, checks each one's schema and price, and runs it from one prepaid balance or by x402, over MCP, a CLI or REST. Top strength x402 on Top weakness No rate-limit numbers, no SLA and no idempotency key on paid runs were found. |
||||||||||||
| 1063 | AgentWebAgent Web Labs, Inc. · MCP server | Tool access | D | 52.4 | 2.8 (4) | n/a | n/a | $0.05 / call | OAuth or key | Hosted | ||
|
AgentWeb, from Agent Web Labs, Inc., is a hosted MCP server and REST API that runs pre-mapped actions on websites, such as searching, booking, messaging and ordering, through the user's own connected site accounts. Top strength Every one of 22 tools carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint, and Top weakness No public changelog, no source and no official SDK; the API and the registry entry are at 0.9.0 |
||||||||||||
| 1527 | SmitherySmithery (Arcade.dev) · HTTP API | Tool access | F | 4.6 | none | n/a | n/a | Freemium | OAuth or key | Hosted | ||
|
Discontinued hosted connection service and API for MCP servers from Smithery, part of Arcade.dev, shut down on 31 October 2026. smithery.ai remains a public directory of MCP servers with no API. Top strength Smithery's notice names what stopped on 31 October 2026 and says every paid charge since 5 August 2026 is refunded Top weakness The API, Connect, accounts, API keys, CLI and SDKs stopped working on 31 October 2026, per Smithery's notice |
||||||||||||
Nothing matches these filters. .
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; the table is complete without JavaScript.
How we test this category
The same task across email, CRM and a database, driven by an agent through each service. We compare connection setup, how each end user authorises, action coverage, retries, logs and the cost per completed run.
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.