sadiuysal/crawl4ai-mcp-server

🕷️ A lightweight Model Context Protocol (MCP) server that exposes Crawl4AI web scraping and crawling capabilities as tools for AI agents. Similar to Firecrawl's API but self-hosted and free. Perfect for integrating web scraping into your AI workflows with OpenAI Agents SDK, Cursor, Claude Code, and other MCP-compatible tools.

48
/ 100
Emerging

This is a self-hosted server that helps AI agents access web content. It takes URLs, domain names, or sitemaps and extracts information from web pages or entire websites. The output is structured markdown content and metadata that your AI workflow can readily use. It's designed for AI developers, researchers, or anyone building AI agents that need to gather information directly from the internet.

Use this if you are building AI agents (e.g., with OpenAI Agents SDK, Cursor, Claude Code) and need them to perform web scraping or crawling to gather information.

Not ideal if you need a simple, standalone web scraping tool that doesn't integrate with AI agents, or if you prefer a managed, cloud-based API service.

AI-agent-development web-data-collection AI-workflow-automation information-retrieval developer-tools
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

60

Forks

9

Language

Python

License

MIT

Category

web-scraping-mcp

Last pushed

Feb 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sadiuysal/crawl4ai-mcp-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.