ai-agents-api-library

AI Agents Accessible APIs

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. For AI products used by humans through a web UI, see the Excluded services section.

AI Agents Accessible APIs is an open, bilingual (English/Polish) catalog of 301 verified services in 26 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.

Contents

1. Machine-readable access (for AI agents)
2. Inclusion criteria
3. Legend
4. Web search (14) · Web scraping and browser automation (18) · Knowledge and research data (12) · Image generation and editing (10) · Video generation and editing (15) · Speech and audio (13) · Music generation (6) · 3D generation and assets (7) · Architecture, CAD and BIM (9) · Diagrams and software architecture (9) · Design and UI (6) · Documents, OCR and presentations (14) · Translation and language (6) · Code execution sandboxes (10) · Developer platforms and DevOps (17) · Databases, vector stores and memory (18) · Email, messaging and chat (13) · Voice agents and telephony (8) · Productivity and workspace (16) · CRM, support and marketing (8) · Social media (10) · Maps, geolocation and weather (11) · Finance, payments and market data (13) · E-commerce (7) · Automation and integration platforms (14) · Model APIs and inference (17)
5. Excluded services
6. Related directories and registries
7. Contributing
8. See also
9. References

Machine-readable access (for AI agents)

AI agents should not parse this page. Fetch one of these stable files instead:

File	Raw URL
llms.txt — short index for LLMs, links to everything below	https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/llms.txt
llms-full.txt — the whole catalog as compact plain text, one line per service	https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/llms-full.txt
catalog/all.json — full catalog, one JSON array	https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/all.json
catalog/<category>.json — one file per category, for small context windows	https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/
data/schema.json — JSON Schema of an entry	https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/data/schema.json

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.

MCP server

The catalog is also an MCP server with four tools: search_apis (filters: query, category, mcp, no_auth, free_tier, auth), get_api, get_reviews (user reviews with pros and cons) and list_categories. No key needed. Add it to your MCP client:

{
  "mcpServers": {
    "ai-agents-api-library": {
      "command": "npx",
      "args": ["-y", "github:eater2/ai_agents_api_library"]
    }
  }
}

Claude Code: claude mcp add ai-agents-api-library -- npx -y github:eater2/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.

Claude skill and plugin

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:

• Claude Code plugin (skill + MCP server):

  /plugin marketplace add eater2/ai_agents_api_library
  /plugin install ai-agents-api-library@eater2
  

• Skill only, Claude Code: copy skills/ai-agents-api-library/ to ~/.claude/skills/ (all projects) or .claude/skills/ (one project).
• Skill only, claude.ai / Claude Desktop: download the skill zip and upload it under Settings → Capabilities → Skills.

Inclusion criteria

• The service exposes a public, self-serve programmatic interface (REST, GraphQL, SDK) or an MCP server.
• A human needs to act at most once — sign up and create a key or approve OAuth. After that the agent works unattended.
• The interface is documented and currently active (verified on the date shown in the infobox).
• Consumer-only apps, waitlists, sales-gated enterprise products, agent frameworks and IDEs are excluded — they are agents or tools for building agents, not services an agent calls.

Legend

• MCP ✅ — official MCP server maintained by the vendor
• MCP ◐ — community-maintained MCP server
• MCP — — no MCP server known; use the REST API
• 🆓 — free tier or free usage without payment
• ★ (date) — proof under the service name: SourceForge rating and review count, GitHub stars, Smithery uses — linked, with the date fetched

Web search

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

Service	What an agent can do	Auth	MCP	Free tier	Docs
Brave Search API	Lets an agent query Brave's independent web/image/video/news search index and get cited, LLM-ready results.	API key	✅	🆓 $5 free monthly credits (~1,000 queries on Search plan); credit card required at signup as anti-fraud measure	docs
Exa	Lets an agent run neural or keyword web search, retrieve page contents, and find similar links via Exa's API.	API key	✅	🆓 free tier: $10 free credits/month (~1,400 searches), no payment method required	docs
Jina AI Search / Reader	Search the web or convert any URL into clean LLM-ready markdown via simple HTTP GET requests.	API key	—	🆓 no key needed: 100 RPM (s.jina.ai search) / 500 RPM (r.jina.ai reader); free API key raises limits to 1,000/5,000 RPM with token-based billing	docs
Kagi Search API	Run programmatic, ad-free premium web/news/image/video searches and extract page markdown via a paid REST API.	API key	✅	no free tier: pay-per-use, $12 per 1,000 search requests, invoiced monthly or at $100 usage, whichever first	docs
Linkup	Lets an agent search, fetch pages, or run deep multi-source research via Linkup's Search/Fetch/Research API endpoints.	API key	✅	🆓 $20 free credits/month for new accounts signing up with a professional email	docs
Mojeek Search API	Query Mojeek's independent web index for titles, URLs and snippets in JSON or XML, with country/language boosting.	API key	—	limited-query free trial available on request; paid plans from £2 CPM (Startup, 5 req/s, 100k/day cap)	docs
Parallel Web Systems Search API	Lets an agent run Parallel's low-latency Search API for web research, content extraction, and entity discovery.	API key	✅	🆓 free: 5,000 requests/month across APIs, plus up to $80 signup credit and $5/month free credits	docs
Perplexity Sonar / Search API	Lets an agent call Perplexity's Search API or MCP tools (search/ask/research/reason) for real-time grounded web answers.	API key / OAuth	✅	no confirmed free tier; pay-as-you-go, Search API billed at $5 per 1,000 requests	docs
SearchApi.io	Fetch structured JSON results from Google, Bing, YouTube, Amazon, TikTok and 50+ other search engines via one REST API.	API key	—	🆓 100 free requests, no credit card required; then paid plans from $40/mo (10,000 searches)	docs
SearXNG (self-hosted JSON API)	Query a self-hosted SearXNG metasearch instance's JSON API to aggregate results from many search engines at once.	none	◐	🆓 free, no key (self-hosted; you run and pay for the instance yourself)	docs
SerpApi	Lets an agent scrape structured JSON results from Google and 20+ other search engines via SerpApi's REST API.	API key	✅	🆓 free plan: 250 searches/month, 50 requests/hour throughput	docs
Serper	Lets an agent fetch fast, low-cost Google search results (web, images, news, maps, shopping) via Serper's REST API.	API key	◐	🆓 free tier: 2,500 queries, no credit card required	docs
Tavily	Lets an agent call Tavily's search API or MCP server to run web searches and get AI-ready summarized results.	API key	✅	🆓 free tier: 1,000 API credits/month, no credit card required	docs
You.com API	Lets an agent call You.com's Search/Answer/Research API or MCP server for LLM-ready web search and grounded answers.	API key	✅	🆓 free credits on signup via you.com/platform; free search profile also available through the keyless Docs MCP server	docs

Web scraping and browser automation

Crawl, scrape and convert pages to Markdown/JSON, or drive a remote headless browser (clicks, forms, logins). — 18 services. JSON: catalog/web-scraping-browser.json

Service	What an agent can do	Auth	MCP	Free tier	Docs
Anchor Browser	Provision authenticated cloud browser sessions and turn any website into callable MCP tools for agents.	API key	✅	🆓 $5 free credits/mo, no card required	docs
Apify	Run web scraping/automation 'Actors' from a marketplace of thousands, and manage datasets, via REST API or MCP server.	API key / OAuth	✅	🆓 free plan: $5/mo platform usage credit, no card required	docs
Bright Data	Access Web Unlocker, SERP API, Scraping Browser, and structured datasets via REST API or MCP to pull web data at scale.	API key	✅	🆓 free tier: up to 5,000 requests/mo	docs
Browse AI API	Trigger pre-built or custom 'robots' to extract and monitor web data via REST API, returning structured JSON.	API key	—	🆓 free forever plan: 50 credits/mo, no card required	docs
Browser Use Cloud API	Launch cloud browser sessions and run AI browser-automation agent tasks via REST API or Python/TypeScript SDK.	API key	—	$15 one-time signup credit for new accounts (Google/GitHub/Microsoft); paid usage afterward	docs
Browserbase (+ Stagehand)	Run and control cloud headless browsers programmatically, with Stagehand adding natural-language page actions.	API key	✅	🆓 free tier: limited browser hours, single concurrency, no card required	docs
Diffbot	Automatically extract structured data (articles, products, people) from any URL via REST API, no custom parsing rules needed.	API key	—	🆓 free plan: 10,000 credits/mo, no card required (5 req/min limit)	docs
Firecrawl	Scrape, crawl, and extract structured data from any website via a single REST API call.	API key	✅	🆓 free tier: 1,000 credits/mo, no card required	docs
Hyperbrowser	Spin up cloud browsers and call scrape, crawl, and structured-extract endpoints via REST API or MCP server.	API key	✅	🆓 free plan: starter credits, 1 concurrent browser, no card required	docs
Oxylabs	Fetch web pages, search-engine results, and e-commerce data at scale via REST API with built-in proxy/unblocking infrastructure.	API key	—	🆓 free trial available (check pricing)	docs
Playwright MCP (Microsoft)	Official Microsoft MCP server giving agents structured browser control (click, type, navigate) via Playwright's accessibility tree.	none	✅	🆓 free, open source, no key	docs
ScrapeGraphAI API	Use AI-driven prompts to scrape and extract structured data from webpages via REST API or Python/JS SDK.	API key	—	🆓 free plan: 500 one-time API credits	docs
ScraperAPI	Scrape any webpage with automatic proxy rotation, CAPTCHA handling, and JS rendering via a single REST API call.	API key	—	5,000 free API credits (trial), no long-term free plan	docs
Scrapfly	Scrape webpages, run cloud browsers, and capture screenshots via REST API or hosted MCP server with anti-bot bypass.	API key / OAuth	✅	🆓 1,000 free credits/mo, no card required, no time limit	docs
ScrapingBee	Scrape any webpage with JS rendering, proxy rotation, and screenshot capture via a single REST API call.	API key	—	🆓 1,000 free API credits, no card required	docs
Spider.cloud	Crawl and scrape websites at scale, returning JSON/XML/CSV, via REST API, CLI, or MCP server.	API key	✅	🆓 keyless trial: 25 free runs/day, no account required	docs
Steel	Create managed cloud browser sessions with stealth proxies and CAPTCHA solving, controllable via REST API or Playwright/Puppeteer.	API key	—	🆓 Hobby tier: 100 browser-hours/mo, 500 requests/day, no card required	docs
Zyte API	Fetch and auto-extract web pages (HTML, browser rendering, product/article data) via one HTTP API with ban avoidance.	API key	—	🆓 $5 free credit for the first month	docs

Knowledge and research data

Encyclopedias, academic papers, news, computational knowledge and up-to-date library documentation. — 12 services. JSON: catalog/knowledge-research.json