MCP Google Custom Search Server

🚀 MCP Google Custom Search Server

A Model Context Protocol (MCP) server that provides web search functionality through Google's Custom Search API. This server enables Large Language Models (LLMs) to perform web searches via a standardized interface.

🚀 Quick Start

Prerequisites

Before you begin, make sure you have:

1. A Google Cloud project with the Custom Search API enabled:

   • Access the Google Cloud Console.
   • Enable the Custom Search API.
   • Create API credentials.

2. A Custom Search Engine ID:

   • Visit the Programmable Search Engine.
   • Create a new search engine.
   • Obtain your search engine ID.

3. Local development requirements:

   • Node.js (v18 or higher).
   • npm (comes with Node.js).

Steps

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-google-custom-search-server.git
   cd mcp-google-custom-search-server
   

2. Install dependencies:

   npm install
   

3. Create an .env file:

   GOOGLE_API_KEY=your-api-key
   GOOGLE_SEARCH_ENGINE_ID=your-search-engine-id
   

4. Build the server:

   npm run build
   

5. Start the server:

   npm start
   

✨ Features

• Seamless integration with Google Custom Search API.
• Server implementation compliant with the Model Context Protocol (MCP).
• Safe type implementation using TypeScript.
• Configuration via environment variables.
• Input validation using Zod.
• Configurable search results (up to 10 per query).
• Formatted search results including title, URL, and description.
• Error handling and validation.
• Compatibility with Claude Desktop and other MCP clients.

🔧 Configuration

Environment Variables

Claude Desktop Integration

Add this configuration to your Claude Desktop configuration file (usually located at ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "googleCustomSearchMCP": {
      "url": "http://localhost:3000",
      "id": "your-server-id"
    }
  }
}

📚 Documentation

Search Tool

To perform a search, send a POST request to the /search endpoint:

{
  "queries": ["your-search-query"]
}

The response will have the following structure:

Project Structure

mcp-google-custom-search-server/
├── src/
│   ├── server.ts          # Main server file
│   └── search.ts         # Search processing logic
└── package.json        # Project dependencies and scripts

Available Scripts

📄 License

[License Link]

🙏 Acknowledgments

Thank you for using our MCP Custom Search Server. If you have any questions or suggestions, please feel free to contact us.