Gemini Search MCP Server

🚀 Using Gemini Search in an MCP Server

An MCP server that uses the Gemini API and Google Search to generate answers based on the latest information.

⚠️ Important Note

This MCP server cannot run independently. It needs to be used in conjunction with an AI assistant (e.g., Cline). After loading this project into the AI assistant, the Gemini search function will be enabled.

🚀 Quick Start

This MCP server combines the Gemini API and Google Search to generate up - to - date answers. However, it must be used with an AI assistant.

✨ Features

Tools

• search - Generate answers using Gemini 2.0 and Google Search
  • It takes a query as input and returns Gemini's response along with relevant search results.

📦 Installation

Step 1: Install Dependencies

npm install

Step 2: Build the Project

npm run build

Step 3: Set Environment Variables

Create a .env file in the project root directory with the following content:

GEMINI_API_KEY=your_api_key_here

⚠️ Important Note: You can obtain the Gemini API key at Google AI Studio.

💻 Usage Examples

Development

For automatic building during development:

npm run watch

Installation Guide for Claude Desktop

When using it with Claude Desktop, add the following configuration:

Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "gemini": {
      "command": "node",
      "args": ["path/to/gemini-search-server/build/index.js"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Debugging

Since the MCP server communicates via stdio, we recommend using MCP Inspector for debugging:

npm run inspector

The Inspector will provide a URL to access the debugging tool in the browser.

📄 License

The code of this project is released under the MIT License. However, please note that this project uses the Google Gemini API, which is subject to Google's Terms of Service. When using this MCP server, you must comply with both the MIT license of our code and Google's Terms of Service for the Gemini API.