Connects to a Crawl4AI docker API server, allowing interaction with Crawl4AI's web crawling functionality through the Model Context Protocol.
Click on "Deploy 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 Server crawl 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.
This MCP Server helps you connect to your Crawl4AI docker API server.
Built with gkzhb/fastmcp-template: TypeScript MCP Server Template.
Prerequisites:
Node.js 18+
To start Crawl4AI MCP server:
export CRAWL4AI_URL=http://your-server-ip:port
npx -y @gkzhb/crawl4ai-mcpNotice that the command above is for Crawl4AI server v0.6.x.
For Crawl4AI server before v0.6.0, please use 0.0.x:
npx -y @gkzhb/crawl4ai-mcp@0.0.8This 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_URL
BROWSERLESS_TOKEN
BROWSERLESS_BLOCK_ADS
BROWSERLESS_STEALTH_MODE
This server cannot be deployed
Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.
Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents
Web pages, PDFs and search results as LLM-ready Markdown or chunks. Firecrawl-compatible, EU-hosted.
