MCP cover image

风力冲浪和自定义MCP服务器之间的集成

1

Github Watches

0

Github Forks

1

Github Stars

MCP Server for Windsurf

Master Control Program (MCP) server that provides additional tools for the Windsurf agentic IDE.

Overview

This MCP server is designed to extend Windsurf's capabilities by providing additional tools that aren't built into Windsurf. It uses FastAPI to create a robust API server with WebSocket support for real-time communication with Windsurf.

Features

  • FastAPI Backend: High-performance, easy-to-use framework
  • WebSocket Support: Real-time bidirectional communication
  • Extensible Tool System: Easily add new tools to extend Windsurf
  • RESTful API: HTTP endpoints for tool execution
  • Windsurf Integration: Seamless integration with Windsurf IDE

Project Structure

MCP_servers/
├── main.py                 # Main FastAPI application
├── tools.py                # Custom tool implementations
├── windsurf_integration.py # Windsurf integration module
├── requirements.txt        # Project dependencies
└── README.md               # Documentation

Built-in Tools

The MCP server comes with several built-in tools:

  1. File Search: Search for files in a directory with pattern matching
  2. Code Analysis: Analyze code files for syntax, complexity, and dependencies
  3. Web Request: Make HTTP requests to external APIs

Installation

  1. Clone the repository
  2. Create a virtual environment:
    python -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
    
  3. Install dependencies:
    pip install -r requirements.txt
    

Usage

  1. Start the MCP server:

    python main.py
    

    This will start the server on http://localhost:8089

  2. Connect Windsurf to the MCP server by configuring the WebSocket connection to:

    ws://localhost:8089/ws
    
  3. Access the API documentation at http://localhost:8089/docs

Adding Custom Tools

To add a new tool to the MCP server:

  1. Open tools.py
  2. Use the @register_tool decorator to register your tool:
@register_tool(
    name="my_custom_tool",
    description="Description of what the tool does",
    parameters={
        "param1": {"type": "string", "description": "Description of parameter 1"},
        "param2": {"type": "integer", "description": "Description of parameter 2"}
    }
)
async def my_custom_tool_handler(params: Dict[str, Any]) -> Any:
    # Tool implementation
    param1 = params.get("param1", "")
    param2 = params.get("param2", 0)
    
    # Do something with the parameters
    result = f"Processed {param1} with value {param2}"
    
    return {"output": result}

API Endpoints

  • GET /: Server information
  • GET /tools: List all available tools
  • POST /tools/{tool_name}: Execute a specific tool
  • WebSocket /ws: WebSocket endpoint for real-time communication

License

MIT

相关推荐

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • Lists Tailwind CSS classes in monospaced font

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • modelcontextprotocol
  • 模型上下文协议服务器

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

  • ravitemer
  • 一个功能强大的Neovim插件,用于管理MCP(模型上下文协议)服务器

  • jae-jae
  • MCP服务器使用剧作《无头浏览器》获取网页内容。

  • patruff
  • Ollama和MCP服务器之间的桥梁,使本地LLMS可以使用模型上下文协议工具

  • n8n-io
  • 具有本机AI功能的公平代码工作流程自动化平台。将视觉构建与自定义代码,自宿主或云相结合,400+集成。

  • WangRongsheng
  • 🧑‍🚀 llm 资料总结(数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型)|摘要世界上最好的LLM资源。

    Reviews

    2 (1)
    Avatar
    user_kyxRHqIF
    2025-04-18

    The windsurf-mcp-integration is an exceptional tool for seamless MCP integration. As an avid MCP application user, I found its functionality to be top-notch and highly reliable. Kudos to rohanbanda-TRT for creating such efficient software. The user guide is clear and easy to follow, making the implementation process smooth and hassle-free. Highly recommend!