Google Search MCP Server

🚀 Google Search MCP Server

An MCP server implementation integrating Google Custom Search JSON API, providing web search functionality.

🚀 Quick Start

The Google Search MCP Server integrates Google's Custom Search JSON API to offer network search capabilities. It comes with various features and configurations to meet different search needs.

✨ Features

• Web Search: Search Google with comprehensive query options.
• Advanced Filtering: Control search results by date, language, country, and safe search level.
• Rate Limiting: Built - in rate limiting to prevent exceeding API quotas.
• Structured Results: Return formatted search results, including titles, URLs, and excerpts.

🛠️ Tools

google_search

• Execute Google searches with advanced filtering options.
• Inputs:
  • query (string): Search term (required).
  • num_results (number, optional): Number of results (1 - 10, default: 5).
  • date_restrict (string, optional): Filter by date (e.g., "d1" for the past day).
  • language (string, optional): 2 - character language code (e.g., "en").
  • country (string, optional): 2 - character country code (e.g., "us").
  • safe_search (string, optional): Safety level ("off", "medium", "high").

⚙️ Configuration

Obtain API Keys

1. Create a Google Cloud project on Google Cloud Console.
2. Activate the Custom Search JSON API on API Dashboard.
3. Generate an API key through the Credentials section or follow the Custom Search API Guide.
4. Get the search engine ID by setting up a custom search engine on Google's Programmable Search.

Environment Variables

Set these variables before running the server:

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

🚂 Run from Local Repository

Steps to run the server directly from the source code:

1. Clone the Repository

git clone https://github.com/ayush-rudani/google-search-mcp-server.git
cd google-search-mcp-server

2. Install Dependencies

pnpm install
# or
npm install

3. Build the Project

pnpm run build
# or
npm run build

4. Configure Claude Desktop

Update your claude_desktop_config.json:

{
  "mcpServers": {
    "google-search": {
      "command": "/path/to/node", // <--- Run `echo "$(which node)"` in the terminal to get the path
      "args": ["/full/path/to/google-search-mcp/index.js"],
      "env": {
        "GOOGLE_API_KEY": "your-api-key",
        "GOOGLE_SEARCH_ENGINE_ID": "your-search-engine-id"
      }
    }
  }
}

• Replace /path/to/node with the full path to the Node.js executable on your system.

5. Test the Server

export GOOGLE_API_KEY=your_api_key_here
export GOOGLE_SEARCH_ENGINE_ID=your_engine_id_here
node dist/index.js

⏱️ Rate Limiting

The server has a default rate limit of 10 requests per minute to prevent exceeding Google's API quotas. You can adjust this setting in the code.

📄 License

This MCP server is released under the MIT License. For more details, see the LICENSE file.