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.

42
/ 100
Emerging

Implements a stdio-based MCP server using Playwright for browser automation, exposing granular tools for single-page scraping (`scrape`), multi-page breadth-first crawling (`crawl`), and large-scale sitemaps (`crawl_site`/`crawl_sitemap`) with optional persistent storage to disk. Supports adaptive crawling that intelligently stops when sufficient content is gathered, safety constraints blocking private IPs, and integration with OpenAI Agents SDK, Cursor, and Claude Code through standardized MCP configuration.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 9 / 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.