sadiuysal/crawl4ai-mcp-server

89 stars ยท Last commit 2026-02-06

๐Ÿ•ท๏ธ 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.

README preview

# Crawl4AI MCP Server

๐Ÿ•ท๏ธ **A lightweight Model Context Protocol (MCP) server that exposes [Crawl4AI](https://docs.crawl4ai.com/) 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.

## Features

- **๐Ÿ”ง MCP Tools**: Exposes 4 powerful tools: `scrape`, `crawl`, `crawl_site`, `crawl_sitemap` via stdio MCP server
- **๐ŸŒ Web Scraping**: Single-page scraping with markdown extraction
- **๐Ÿ•ท๏ธ Web Crawling**: Multi-page breadth-first crawling with depth control
- **๐Ÿง  Adaptive Crawling**: Smart crawling that stops when sufficient content is gathered
- **๐Ÿ›ก๏ธ Safety**: Blocks internal networks, localhost, and private IPs
- **๐Ÿ“ฑ Agent Ready**: Works with OpenAI Agents SDK, Cursor, and Claude Code
- **โšก Fast**: Powered by Playwright and Crawl4AI's optimized extraction

## ๐Ÿš€ Quick Start

Choose between **Docker** (recommended) or **manual installation**:

View full repository on GitHub โ†’