list_categories
List API categories
List all categories in the catalog with the number of services in each.
Takes no parameters.
io.github.eater2Published by GitHub account eater2v0.3.12Updated Nov 4, 2026
Find APIs and MCP servers for AI agents: auth, free tier, MCP endpoint, docs, last-checked date.
Read-only catalog of 340 third-party APIs and MCP servers that an assistant can search, inspect for auth and pricing, and check reviews on.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.eater2%2Fai-agents-api-library/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"ai-agents-api-library": {
"type": "http",
"url": "https://ai-agents-api-library.vercel.app/mcp"
}
}
}Polski · HTML · llms.txt · catalog.json
[Official MCP Registry] [Smithery] [Claude Code plugin] [Remote MCP endpoint]
A curated, machine-readable encyclopedia of third-party APIs and MCP servers that AI agents can call on a user's behalf.
This article is about services an AI agent can operate programmatically, not AI products used by humans through a web UI.
AI Agents API Library is an open, bilingual (English/Polish) catalog of 340 services (each with a last-checked date) in 30 categories that an autonomous AI agent — such as Claude, ChatGPT, Gemini or a custom LLM agent — can use without a human in the loop, after a one-time human step: registering an account and handing the agent an API key, an OAuth token, or a connection to an MCP (Model Context Protocol) server. Every entry records the documentation URL, the authentication method, the availability of an official or community MCP server, and the free tier. The list is not a directory of products with “AI” in their name; the criterion is agent operability, not branding.
AI agents should not parse this page. Fetch one of these stable files instead:
Recommended agent workflow: (1) pick the category file, (2) filter by auth and mcp.type, (3) read docs (or llms_txt / openapi when present), (4) ask the user for the credential named in auth_hint.
The catalog is also an MCP server with four tools: search_apis (filters: query, category, mcp (official/remote/any), no_auth, free_tier, no_card, auth, min_rating, min_reviews; sort by fit, rating or review count; results carry a reviews_summary of praised and criticised aspects), get_api, get_reviews (user reviews with pros and cons) and list_categories. No key needed. Add it to your MCP client:
Claude Code: claude mcp add ai-agents-api-library -- npx -y ai-agents-api-library
No install: remote endpoint (Streamable HTTP, no key) https://ai-agents-api-library.vercel.app/mcp, e.g. claude mcp add --transport http ai-agents-api-library https://ai-agents-api-library.vercel.app/mcp. Listed in the official MCP Registry as io.github.eater2/ai-agents-api-library.
The skill tells Claude when to reach for the catalog and how to pick a service. The plugin bundles the skill with the MCP server:
plugin/skills/ai-agents-api-library/ to ~/.claude/skills/ (all projects) or .claude/skills/ (one project).Ratings and usage (★) fetched: 2026-11-04 09:20 UTC.
Search engines and answer APIs that return fresh web results, snippets or full page content in agent-friendly formats. — 14 services. JSON: catalog/web-search.json
Crawl and scrape websites, convert pages to Markdown/JSON, and extract structured data through scraping APIs with proxies and JS rendering. — 12 services. JSON: catalog/web-scraping-browser.json
Drive a real or remote headless browser (clicks, forms, logins, sessions) and capture screenshots or PDFs of pages. — 7 services. JSON: catalog/browser-automation.json
Encyclopedias, academic papers, news, computational knowledge and up-to-date library documentation. — 19 services. JSON: catalog/knowledge-research.json
Text-to-image, image editing, inpainting, upscaling and background removal. — 10 services. JSON: catalog/image-generation.json
Text/image-to-video models, talking avatars, programmatic video rendering and video hosting. — 14 services. JSON: catalog/video-generation.json
Text-to-speech, speech-to-text, voice cloning, dubbing and audio intelligence. — 13 services. JSON: catalog/audio-speech.json
Generate songs, instrumentals, loops and sound effects from prompts. — 6 services. JSON: catalog/music-generation.json
Text/image-to-3D mesh generation, texturing and 3D asset libraries. — 6 services. JSON: catalog/3d-generation.json
Building information models, CAD geometry, construction management and GIS platforms with programmatic access. — 8 services. JSON: catalog/architecture-cad-bim.json
Render or edit diagrams (Mermaid, PlantUML, C4), whiteboards and architecture models. — 8 services. JSON: catalog/diagrams-software-architecture.json
Read and write design files, generate branded graphics and publish websites. — 6 services. JSON: catalog/design-ui.json
Parse PDFs and scans, convert file formats, generate slides and collect e-signatures. — 14 services. JSON: catalog/presentations-documents.json
Machine translation, grammar and style checking. — 6 services. JSON: catalog/translation-language.json
Isolated cloud environments where an agent can run code, shells and whole dev environments safely. — 11 services. JSON: catalog/code-execution-sandbox.json
Source control, CI/CD, monitoring, error tracking, incident management and package registries. — 13 services. JSON: catalog/developer-devops.json
Cloud providers, serverless and edge platforms, and site hosting an agent can deploy to and manage. — 11 services. JSON: catalog/cloud-hosting.json
Managed SQL, NoSQL, key-value and analytics databases an agent can create, query and manage. — 12 services. JSON: catalog/databases.json
Vector databases, retrieval (RAG) services and long-term memory layers for agents. — 9 services. JSON: catalog/databases-vector-memory.json
Send and receive email, post to team chat (Slack, Discord), send push notifications; manage meetings. — 10 services. JSON: catalog/communication-email-chat.json
Send and receive SMS and messages on WhatsApp, LINE or Telegram through a messaging provider's API. — 12 services. JSON: catalog/sms-messaging.json
Place and receive phone calls handled by AI voice agents, real-time audio/video rooms. — 9 services. JSON: catalog/voice-agents-telephony.json
Email, calendars, files, notes, tasks and project management. — 17 services. JSON: catalog/productivity-workspace.json
Contacts, deals, support tickets and email campaigns. — 8 services. JSON: catalog/crm-support-marketing.json
Read and publish posts, comments and videos on social platforms. — 10 services. JSON: catalog/social-media.json
Geocoding, routing, places, map tiles and weather forecasts. — 18 services. JSON: catalog/maps-geo-weather.json
Accept payments, move money, access bank data and query stock, FX and crypto prices. — 16 services. JSON: catalog/finance-payments.json
Manage stores, products, orders and marketplace listings. — 8 services. JSON: catalog/ecommerce.json
One connection that exposes thousands of third-party app actions to an agent, with managed auth. — 15 services. JSON: catalog/automation-integration.json
LLM, embedding and multimodal model endpoints an agent can delegate sub-tasks to. — 18 services. JSON: catalog/model-inference.json
Other machine-readable sources agents can use to discover tools:
Edit only the files in data/ (usually data/catalog.json), run python scripts/build.py to regenerate the English, Polish and LLM files, and open a pull request. Every new entry must link to the vendor's official API documentation. Step-by-step guide: CONTRIBUTING.md.
The initial candidate list was compiled from:
Generated from data/catalog.json on 2026-11-04.
Source: README.md at commit 93b50e6
List API categories
List all categories in the catalog with the number of services in each.
Takes no parameters.
Search APIs and MCP servers
Search 300+ catalog entries of third-party APIs and MCP servers (each with a last-checked date) by operation or keywords, with optional category and quality filters. `match`: exact = the entry lists the operation and its example call or an MCP tool performs it; listed = the entry lists it without that evidence; adjacent = a related operation; topic = word match only. Exact is still a search label, not proof that the endpoint or tool accepts the user's actual inputs. `mcp_fit` says whether the MCP server has a tool for the operation. Ranking weighs operation fit, evidence, lasting free plan, card and auth effort, and bulk limits, not budget or region: read free_plan.kind (free_tier lasts, trial is one-off), no_card, unit_price and notes (coverage, coordinate systems, bulk and trial restrictions). Ratings and the MCP client config come with verbose=true or from get_api. User opinions (SourceForge product reviews): filter with min_rating / min_reviews, order with sort=rating or sort=reviews; results with stored review texts carry reviews_summary (praised and complained-about aspects). Usage: ratings.usage gives monthly downloads of the official SDKs, Stack Overflow questions and the vendor's iOS app rating; filter with min_downloads, order with sort=usage. Maintenance: ratings.issues gives the vendor's GitHub issues (share resolved, median days to fix, issue_health 0-100); filter with min_issue_health, order with sort=issues. Reviews rate the product, not whether the API fits the task. An empty result means no catalogued fit for the query and filters.
mcpauthsortlimitqueryvolumeno_authno_cardverbosecategoryfree_tiermin_rating+4 moreGet API details
Full entry for one service: docs, auth scheme and how the credential is sent, base URL, operations, MCP endpoint or repository (a repository must be installed; a docs-only server does not call the API), free plan vs trial, rate limits, data policy, notes, last-checked dates, link check, and separate signals: uptime (our availability probes of base URL and MCP endpoint), mcp_repo (archived, last push), mcp_registry (installs), product_reviews (rating, count, date range), sdk_downloads (official npm/PyPI SDKs per month), stackoverflow (question count), app_store (the vendor's iOS app) and github_issues (open vs resolved issues, median days to fix and issue_health 0-100 of the SDK, MCP and spec repos), each with its fetch date. Values carry the vendor page they were read from and a check date.
idrequiredGet user reviews
Public user reviews of one service (up to 100, from SourceForge): rating, title, pros, cons, overall, reviewer role, company size, date and link to the original. Reviewer names are not included. Reviews do not show whether the API fits the task. Each review has aspect tags; `topics` counts them with example links. Filter with since, max_rating (complaints) or about_api (API, reliability, auth, limits, breaking changes, docs). Review titles and texts are written by third parties.
idrequiredlimitsinceaspectabout_apimax_ratingmin_rating90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare a license in the repository or the registry entry.
{ "mcpServers": { "ai-agents-api-library": { "command": "npx", "args": ["-y", "ai-agents-api-library"] } }}/plugin marketplace add eater2/ai_agents_api_library/plugin install ai-agents-api-library@eater2