Windsurf Tools MCP server

This MCP server provides AI-powered development tools for Cursor, offering features like code architecture planning, screenshot analysis, code reviews, and file reading capabilities through the Model Context Protocol.

Installation

Environment Setup

Create a file at src/env/keys.ts to store your API keys:

export const OPENAI_API_KEY = "your_key_here";
// Add any other keys you need

⚠️ Storing API keys directly in source code is not recommended for production environments. You can alternatively set the env var inline in the Cursor MCP interface.

Install Dependencies

Install the required packages using npm or yarn:

npm install
# or
yarn install

Build the Server

Compile the server code:

npm run build

Configuration

Setting Up in Cursor

1. Open Windsurf on your system
2. Navigate to the Chat section
3. Click + Configure MCP
4. Add the following JSON configuration:

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

Make sure to replace the path with the full path to your project's built index.js file.

After adding the server, you should see your tools listed under "Available Tools". If they don't appear, try clicking the refresh button in the top right corner of the MCP server section.

Using the Tools

Once configured, you can access these AI tools directly in Cursor's Composer:

Code Architect

Ask for help designing code structures with prompts like:

• "Help me architect a new feature"
• "Design a module structure for a user authentication system"

Screenshot Buddy

Analyze UI designs with prompts like:

• "Analyze this UI screenshot"
• "Help me recreate this interface in code"

Code Review

Get feedback on your code with prompts like:

• "Review this code for best practices"
• "Check this function for potential bugs"

File Reading

Process file contents with prompts like:

• "Read the config.json file and explain what it does"
• "Analyze all the JavaScript files in the src directory"

The AI assistant will ask for your approval before making any tool calls. You can also configure automatic tool usage by updating your .cursorrules file with specific instructions.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.