drio
Open app

Crawl4AI MCP Server

Source

用于提供给本地开发者的 LLM的高效互联网搜索&内容获取的MCP Server， 节省你的token

Catalog onlyCatalog onlySTDIO

Overview

Crawl4AI MCP Server is an intelligent information retrieval server based on the Model Context Protocol (MCP), designed to provide efficient internet search and content acquisition for local developers, optimizing the use of tokens for AI systems.

To use the server, clone the repository, set up a virtual environment, install dependencies, and configure the search engines. You can perform searches and extract content using the provided tools.

  • 🔍 Powerful multi-engine search capabilities supporting DuckDuckGo and Google. - 📚 LLM-optimized web content extraction, intelligently filtering non-core content. - 🎯 Focus on information value, automatically identifying and retaining key content. - 📝 Multiple output formats supporting citation tracing. - 🚀 High-performance asynchronous design based on FastMCP.
  1. Enhancing AI assistants with robust web search capabilities.
  2. Extracting and understanding web content for LLM applications.
  3. Supporting developers in building AI-driven applications with efficient content retrieval.

Add to your AI client

Use these steps to connect Crawl4AI MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "crawl4ai-mcp-server-weidwonder": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "crawl4ai-mcp-server-weidwonder": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "crawl4ai-mcp-server-weidwonder": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "crawl4ai-mcp-server-weidwonder": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "crawl4ai-mcp-server-weidwonder": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "crawl4ai-mcp-server-weidwonder": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-crawl4ai-mcp-server-weidwonder"
      ]
    }
  }
}

FAQ

Can Crawl4AI MCP Server be used for all types of web searches?

Yes! It supports multiple search engines and is optimized for various content types.

Is there a cost associated with using Crawl4AI MCP Server?

No! The server is free to use for developers.

How does Crawl4AI MCP Server optimize content for LLM?

It uses intelligent content recognition and noise filtering to retain only the most relevant information.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1450,"uuid":"debdf7c0-253b-4132-b3a2-e2e3a609bd40","name":"crawl4ai-mcp-server","title":"Crawl4AI MCP Server","description":"用于提供给本地开发者的 LLM的高效互联网搜索&内容获取的MCP Server， 节省你的token","avatar_url":"https://avatars.githubusercontent.com/u/7799744?v=4","created_at":"2025-02-20T15:52:52.423Z","updated_at":"2025-02-23T07:21:40.839Z","status":"created","author_name":"weidwonder","author_avatar_url":"https://avatars.githubusercontent.com/u/7799744?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/weidwonder/crawl4ai-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/4123480f0c84e62dff0dc0224605e40bbca9f7769e2c2730729d4e9cdfec8eca/68747470733a2f2f736d6974686572792e61692f62616467652f4077656964776f6e6465722f637261776c3461692d6d63702d736572766572","type":null,"metadata":"{\"star\":\"36\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-20 23:38:31\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data