Windsurf Tools

🚀 🤖 AI Development Assistant MCP Server

This project serves as an AI-driven development toolkit designed as a Model Context Protocol (MCP) server for Cursor! It offers intelligent coding assistance through custom AI tools.

⚠️ Important Note

This is a tutorial demonstration project primarily for local development and learning, not a production-ready tool.

✨ Features

🎨 Code Architect

Invoke advanced inference LLMs to generate plans and instructions for coding agents.

📸 Screenshot Helper

Capture UI design screenshots for use with composer agents.

🔍 Code Review

Trigger code reviews via git diffs.

📄 Read Single File & Read Multiple Files

Reading a single file doubles data parsing efficiency, while reading multiple files facilitates batch data processing.

🚀 Quick Start

1. Environment Configuration

First, you need to set up environment variables. Create a file at src/env/keys.ts:

export const OPENAI_API_KEY = "your_key_here";
// Add other required keys

⚠️ Security Tip

Storing API keys directly in source code is not recommended for production environments. This is only for local development and learning purposes. You can also set environment variables directly in the Cursor MCP interface.

2. Installation

npm install
# Or
yarn install

3. Build the Server

npm run build

4. Open Windsurf Chat and Configure MCP

This project is designed as a Cursor MCP server. Here's how to set it up:

1. Open Windsurf on your system.
2. Navigate to the "Chat" section.
3. Click + Configure MCP (this allows you to add a new MCP server).
4. Add the following JSON configuration:

{
  "mcpServers": {
    "mcp-server": {
      "command": "node",
      "args": [
        "D:\\mpc-server\\build\\index.js"
      ]
    }
  }
}

📘 Tip

You may need to use the full path to the project's built index.js file.

After adding the server, you should see your tools under "Available Tools". If not, try clicking the refresh button in the top-right corner of the MCP server section.

For more setup details, refer to the Windsurf MCP Documentation.

💻 Usage Examples

Once configured, you can use these tools directly in Cursor's composer. The AI will automatically suggest relevant tools, or you can explicitly request a tool by its name or description.

For example, try typing the following in the composer:

• "Review this code for best practices"
• "Help me architect a new feature"
• "Analyze this UI screenshot"
• "Read a single file & Read multiple files"

The agent will ask for your approval before invoking any tool.

📘 Tip

You can update the .cursorrules file to add instructions for using tools in specific scenarios, and the agent will use the tools automatically.

🔧 Technical Details

Project Structure

src/
├── tools/
│   ├── architect.ts    # Code structure generator
│   ├── screenshot.ts   # Screenshot analysis tool
│   ├── fileReader.ts  # Read single file & Read multiple files tool
│   └── codeReview.ts   # Code review tool
├── env/
│   └── keys.ts         # Environment configuration (add your API keys here!)
└── index.ts           # Entry point