Connects to a Crawl4AI docker API server, allowing interaction with Crawl4AI's web crawling functionality through the Model Context Protocol.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Crawl4AI MCP Servercrawl the latest AI news from TechCrunch"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Crawl4AI Model Context Protocol Server
This MCP Server helps you connect to your Crawl4AI docker API server.
Built with gkzhb/fastmcp-template: TypeScript MCP Server Template.
Quick Start
Prerequisites:
Node.js 18+
To start Crawl4AI MCP server:
Notice that the command above is for Crawl4AI server v0.6.x.
For Crawl4AI server before v0.6.0, please use 0.0.x:
This MCP server uses Streamable HTTP. And the default Streamable HTTP URL is http://localhost:8585/mcp.
SSE is also supported and the SSE HTTP URL is http://localhost:8585/sse.
To customize MCP server, here are the shell environment variables:
Variable | If Optional | Description |
| Required | Crawl4AI docker API server URL, eg. |
| Optional | If Crawl4AI server enables authentication, you need to use this |
| Optional | MCP server port, default value is |
This MCP also supports Browserless to crawl web page since v0.2.1
See env.ts for Browserless environment variables:
BROWSERLESS_URLBROWSERLESS_TOKENBROWSERLESS_BLOCK_ADSBROWSERLESS_STEALTH_MODE