A MCP server that provides web crawling capabilities using crawl4ai with markdown output for the LLM.
git clone https://github.com/Kirill812/crawl4ai-mcp-server.git
cd crawl4ai-mcp-server
npm install
npm run build
{
"mcpServers": {
"crawl4ai": {
"command": "node",
"args": [
"/path/to/crawl4ai-mcp-server/build/index.js"
],
"env": {
"CRAWL4AI_API_URL": "http://127.0.0.1:11235",
"CRAWL4AI_AUTH_TOKEN": "your-auth-token" // Optional: if authentication is needed
}
}
}
}
Replace the environment variables with your values:
CRAWL4AI_API_URL
: URL of the crawl4ai API service (optional)CRAWL4AI_AUTH_TOKEN
: Authentication token for the API (optional)crawl_urls
- Crawl web pages and get markdown content with citations
urls
(required): List of URLs to crawlThe tool returns markdown content with citations for each URL. Multiple URLs are separated by horizontal rules (---). Example:
This is content from the first URL [^1]
[^1]: https://example.com
---
This is content from the second URL [^2]
[^2]: https://example.org
For development with auto-rebuild:
npm run watch
Common issues and solutions:
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Seamless access to top MCP servers powering the future of AI integration.