Crawl4AI MCP Server

Wraps the Crawl4AI library with a Model Context Protocol (MCP) server, providing crawling functionality via Python functions.

Local serverstdioPython

What is the Crawl4AI MCP Server?

Wraps the Crawl4AI library with a Model Context Protocol (MCP) server, providing crawling functionality via Python functions.

The short version

The Docker image includes Playwright browsers — no separate setup needed.

  • Full MCP compliance — via FastMCP v3 with tool annotations (readOnlyHint, destructiveHint, etc.)
  • 4 focused tools — centered on canonical scrape/crawl plus session lifecycle/artifacts
  • 3 prompts — for common LLM workflows (summarize, extract schema, compare pages)
  • 2 resources — exposing server configuration and version info
  • Headless Chromium — managed as a lifespan singleton (start once, reuse everywhere)
  • Multiple transports — — stdio (default) and Streamable HTTP

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
scrapeScrape one URL or a bounded list of URLs (up to 20) with a single canonical envelope response.
crawl
close_sessionClose a stateful session created via options.session.session_id.
get_artifactRetrieve artifact metadata/content captured during scrape or crawl when options.conversion.capture_artifacts is enabled.

Example prompts to try

  • “Use Crawl4AI to scrape.”
  • “Use Crawl4AI to crawl.”
  • “Use Crawl4AI to close session.”

Frequently asked questions

MCP (Model Context Protocol) is a standardized way for different applications and services to communicate, particularly in AI and data processing workflows. Crawl4AI-MCP uses it to expose its crawling capabilities.