Terminal, page 5 of 5
1021 graded168 agent-ready1236 desk reviews by the panel39 accept x402updated 14 Oct 03:07 UTC
Also indexed, not graded 2,000 indexed MCP servers MCP registry, 42,647 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 995 | ZapiaBrainlogic AI S.A.S. · Platform | Assistants | F | 17.3 | none | n/a | n/a | $9.99 / mo | OAuth or key | Local | ||
|
Zapia is a personal AI assistant app for iOS, Android and the web, aimed at Latin America. It reads connected email, calendars, files and chats, sends reminders, drafts replies and runs scheduled tasks. Top strength Free plan at US$0 that the plans page says isn't a trial, with card payment only for paid plans. Top weakness No API, MCP server or A2A endpoint, and the terms forbid unauthorised automated connections. |
||||||||||||
| 996 | CaddyCaddy Technologies Inc. · Platform | Assistants | F | 16.7 | none | n/a | n/a | Free | OAuth or key | Local | ||
|
Caddy is a hosted personal AI assistant people text over iMessage or RCS. It watches connected mail, calendars and work apps, sends reminders and briefings, and drafts replies and calendar changes for the owner. Top strength Free, with Google sign-in and no card. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 997 | OrbitsNemus AI, Inc. · Platform | Assistants | F | 15.6 | none | n/a | n/a | Paid | OAuth or key | Local | ||
|
Orbits is a household assistant app for iOS and Android with an AI called Bit. It manages family calendars, lists, meals, chores and home upkeep, reads household email, and can place phone calls and build Instacart carts. Top strength Bit places a restaurant call only after the owner approves the restaurant, party size, date, time and name. Top weakness No public agent API, as llms.txt states. |
||||||||||||
| 998 | Natura tinyNatureNatura Inc. · Platform | Assistants | F | 15.1 | none | n/a | n/a | $20 / mo | OAuth or key | Local | ||
|
tinyNature is Natura's personal AI agent, reached over iMessage, WhatsApp, Telegram or the HumanPods earbuds. It sends briefings and reminders and works with the owner's calendar, Gmail and health data. Natura's Interface ring is waitlist only. Top strength A subprocessor table names each provider with data, region and legal basis, and changes get 30 days' notice. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 999 | ZeroEntropy zerank and zembedZeroEntropy · HTTP API | Embeddings | F | 13.7 | 1.0 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Discontinued retrieval API acquired by Notion. Its embedding and reranking models remain available as open weights for self-hosting. Top strength All four models now open weights under Apache 2.0 on Hugging Face Top weakness The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026 |
||||||||||||
| 1000 | TomoMapo Labs, Inc. · Platform | Assistants | F | 13.1 | none | n/a | n/a | $19.99 / mo | OAuth or key | Local | ||
|
Tomo is a personal AI from Mapo Labs that a person texts over iMessage or uses in its iOS app. It remembers goals, checks in first, joins group chats, sets reminders and connects to the owner's calendar and email. Top strength In iMessage group chats it shares only busy times from a connected calendar, not event details. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 1001 | BreaBrea AI LLC · Platform | Assistants | F | 12.9 | none | n/a | n/a | Freemium | OAuth or key | Local | ||
|
Brea is a hosted personal AI assistant people text in iMessage. It replies to email, books flights and handles tasks across more than 2,000 connected apps, and uses a cloud browser for sites without an integration. Top strength Free plan with every feature and no credit card, per the FAQ and docs. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 1002 | SOUNDRAW APISOUNDRAW Inc. · Model API | Music | F | 12 | 1.5 (2) | n/a | n/a | $29.99 / mo | API key | Local | ||
|
Tokyo-based SOUNDRAW's B2B API for royalty-free instrumental background music chosen by genre, mood, theme and length, built into Canva and Filmora. Top strength Trained only on in-house compositions, per SOUNDRAW Top weakness No public API docs, OpenAPI spec, SDK or changelog |
||||||||||||
| 1003 | TabTerrasoft, Inc. · Platform | Assistants | F | 10.7 | none | n/a | n/a | Paid | OAuth or key | Local | ||
|
Tab is a hosted AI assistant in private beta that people text in Messages. It has its own computer and browser, makes phone calls, works with connected accounts, and places orders or pays invoices after the owner approves. Top strength Saved passwords are encrypted and filled inside a separate boundary, with only an opaque ID passed to the AI. Top weakness Private beta behind a waitlist. |
||||||||||||
| 1004 | Bobahumans& ai, inc. · Platform | Assistants | F | 10.3 | none | n/a | n/a | Free | OAuth or key | Local | ||
|
Boba is a free AI assistant people text over iMessage, RCS or SMS, one to one or in group chats. It plans with groups, answers questions, drafts messages, makes and edits images and writes songs. Top strength Free, with no subscription, ads, card or app. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| shut | OpenAI Sora APIShut down 2026-09-24 OpenAI · Model API | Video | F | 9.4 | 1.0 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Discontinued OpenAI video generation API for the Sora 2 and Sora 2 Pro models. Top strength Six months' notice, from 24 March to 24 September 2026 Top weakness Shut down on 2026-09-24, so every call fails |
||||||||||||
| 1005 | HireAlphaHireAlpha · Platform | Assistants | F | 8.4 | none | n/a | n/a | $19 / mo | None | Hosted | ||
|
HireAlpha sells three AI personas, Friend, Coworker and Cofounder, each a separate iMessage or SMS contact with its own number and memory. They read connected Google mail and calendar and track health, work and company tasks. Top strength Public prices, $19 a month a persona and $190 a year for one. Top weakness No terms of service (/terms returns 404) and no legal entity named. |
||||||||||||
| 1006 | asaplyAsaply Inc. · Platform | Assistants | F | 7.6 | none | n/a | n/a | Pay per use | OAuth or key | Local | ||
|
asaply is a hosted errand assistant people text over iMessage or SMS to order coffee and lunch for pickup, buy tickets, book rides and make reservations, with payment through Apple Pay. Top strength The total is shown before anything is confirmed, and Apple Pay keeps the card number from asaply. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 1007 | OverclockOverclock · Platform | Knowledge | F | 7.5 | 1.0 (2) | n/a | n/a | Paid | OAuth | Local | ||
|
Hosted enterprise knowledge platform from Overclock Technologies Limited, a UK company incorporated on 22 July 2026. Top strength The privacy policy says Drive access is read-only and limited to folders a user selects, and Gmail access is read-only Top weakness No public docs, MCP tool definitions, endpoint or llms.txt |
||||||||||||
| 1008 | CoreGhost (ZMJ, Inc.) · Platform | Local AI | F | 7.3 | 2.0 (1) | n/a | n/a | Paid | OAuth or key | Local | ||
|
Core is a personal AI computer from Ghost that runs open-weight language models and a memory of the owner's apps, files and devices at home, used through Ghost's apps and an OpenAI Responses-compatible endpoint. On pre-order. Top strength Ghost says inference and memory run on Core with no remote model fallback, and states no subscription or per-token fee Top weakness Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening |
||||||||||||
| 1009 | InstinctSpear Street Technology, Inc. (d/b/a Instinct) · Platform | Assistants | F | 7.3 | none | n/a | n/a | Paid | OAuth or key | Local | ||
|
Instinct is a hosted personal assistant that a person texts or calls. It uses a phone and a computer on the owner's behalf, connects to Google Workspace and WhatsApp, and handles tasks such as bills, gifts, groceries and appointments. Top strength The privacy policy warns that third parties may plant instructions aimed at autonomous agents and asks owners to review actions. Top weakness No API, MCP server or A2A endpoint for an outside agent. |
||||||||||||
| 1010 | sznNomadic Futures · Platform | Assistants | F | 7.3 | none | n/a | n/a | Free | OAuth or key | Local | ||
|
szn (pronounced season) is a hosted personal assistant that carries out errands end to end. It makes phone calls, sends emails, books and follows up for the owner, reached through its web app, iMessage, SMS and email. Top strength Free during the early preview. Top weakness Early access by access code only. |
||||||||||||
| shut | BaserunShut down 2024-09-30 Baserun · HTTP API | Evals | F | 7 | 1.0 (2) | n/a | n/a | $49 / seat-mo | API key | Hosted | ||
|
Discontinued LLM testing and monitoring platform with Python and JavaScript SDKs for tracing model calls. Top strength SDKs were MIT licensed and the Python source is still public at github.com/baserun-ai/baserun-py Top weakness Service offline since late 2024. api.baserun.ai doesn't resolve and app.baserun.ai serves an expired certificate |
||||||||||||
| shut | Google ImagenShut down 2026-08-17 Google · Model API | Image | F | 6.8 | 1.0 (2) | n/a | n/a | Pay per use | API key | Hosted | ||
|
Discontinued Google image generation models, formerly available through the Gemini API and Vertex AI. Top strength Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named Top weakness Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI |
||||||||||||
| shut | PlayHT Text-to-Speech APIShut down 2025-12-31 PlayHT · Model API | TTS | F | 3.9 | 1.0 (2) | n/a | n/a | Paid | API key | Hosted | ||
|
Discontinued text-to-speech API from PlayHT, formerly supporting streaming audio and batch generation. Top strength The old API reference is still readable at docs.play.ht for anyone porting code Top weakness api.play.ht doesn't resolve, so every call fails |
||||||||||||
| shut | PlayHT Voice Cloning APIShut down 2025-12-31 PlayHT · Model API | Cloning | F | 3.9 | 1.0 (2) | n/a | n/a | Paid | API key | Hosted | ||
|
Discontinued PlayHT service for creating voices from uploaded audio samples. Top strength The API reference is still readable at docs.play.ht, useful for mapping old integrations Top weakness Shut down, api.play.ht doesn't resolve |
||||||||||||
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 listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. 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.