A mega collection of 2,070 AI agent data APIs: MCP servers, LLM tools, RAG pipelines, live web data, vision & voice. Give your AI agent live web data.
Give your AI agent live web data. 2,070 actors for MCP servers, LLM tools, RAG pipelines, browser automation, vision, and voice — powered by production-ready Apify actors.
🔍 Browse the Actor Catalog · 🚀 Start Building · ⚡ Try Apify Free
A mega directory of 2,070 AI agent data APIs — everything an AI agent needs to touch the live web. MCP servers it can call directly, browser actors that read any page, RAG pipelines for knowledge bases, vision and voice models, LLM utilities. Every actor is a ready-to-run Apify worker your agent can invoke as a tool.
- 🔍 Browse the actor catalog — 2,070 actors across MCP servers, LLM tools, RAG, live web data, vision, and voice.
Coverage snapshot This directory ------: 🤖 Verified AI actors 2,070 🔌 MCP servers 170 🧠 LLM & chatbot actors 120 📚 RAG & knowledge bases 56 🌐 Live web data for agents 496 👁️ Vision, image & video AI 252 🎙️ Voice & transcription 107 Starting cost Free tier + pay-per-result
If you need to… Start here ------ 🔌 Let Claude/Codex call web tools directly Agent + MCP playbook 📚 Build a RAG knowledge base from any website RAG pipeline playbook 🌐 Give an agent a live browser Actor catalog → live web data 🧠 Add LLM, vision, or voice capabilities Actor catalog → matching section
- 🔌 Agent + MCP setup — connect an Apify MCP server to Claude or Codex and let the agent call scrapers as tools. The playbook walks through it. - 📚 RAG pipelines — crawl any site, chunk it, embed it, query it. The playbook builds one end to end. - 🌐 Live-data agents — agents that check prices, monitor pages, and research the web on their own schedu
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/cporter202--ai-agent-data-apis.html)
MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl.
SanggonBoy/PyreCrawlWeb browsing superpowers for AI agents - one MCP server to scrape, crawl, extract, map, search, batch, research & monitor the web. Self-hosted, no API keys. Free Firecrawl alternative.
bybit-exchange/kaasTurn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
HasData/web-scraping-mcpMCP server for HasData's Web Scraping API: fetch any public URL through managed proxies, render JavaScript when needed, and get markdown, text, HTML or structured JSON. From 1 credit a call.
graphersal/graphersalIn-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.
bimal1023/AI-native-engineerTracking my journey into AI engineering, one module at a time. Fundamentals to agents, with hands-on projects. Open to all.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.