Gemini Search MCP Server

An MCP server that generates responses based on the latest information using the Gemini API and Google Search.

Note : This MCP server does not work standalone. It needs to be used in combination with AI assistants like Cline . The Gemini search functionality becomes available when you load this project into an AI assistant.

An MCP server that uses the Gemini API and Google search to generate answers based on up-to-date information.

Note : This MCP server does not work alone. It must be used in conjunction with an AI assistant such as Cline . By loading this project into the AI assistant, the Gemini search function will become available.

Features

Tools

• search - Generate answers using Gemini 2.0 and Google Search

  • Takes a query as input and returns Gemini's response along with relevant search results

Related MCP server: MCP Gemini API Server

function

Tools

• search - Answer questions using Gemini 2.0 and Google search

  • It takes a query as input and returns Gemini's answers and relevant search results.

Setup

1. Install dependencies:

npm install

2. Build:

npm run build

3. Set environment variables: Create a .env file in the project root with the following content:

GEMINI_API_KEY=your_api_key_here

Note: You can get your Gemini API key from Google AI Studio .

Development

For automatic builds during development:

npm run watch

Installation

To use 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 MCP servers communicate via stdio, we recommend using MCP Inspector for debugging:

npm run inspector

The Inspector provides a URL to access debugging tools in your browser.

License

The code in 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 for our code and Google's terms for the Gemini API.

set up

1. Install dependencies:

npm install

2. Build:

npm run build

3. Set environment variables: Create a .env file in the root of your project with the following content:

GEMINI_API_KEY=your_api_key_here

*Gemini API key can be obtained from Google AI Studio .

development

Automated development builds:

npm run watch

install

To use 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"
      }
    }
  }
}

debug

Since MCP servers communicate via stdio, we recommend using MCP Inspector for debugging:

npm run inspector

Inspector provides a URL to access the debugging tools in your browser.

license

The code for this project is released under the MIT License . However, because this project uses the Google Gemini API, it is also subject to Google's terms of service . When using this MCP server, you must comply with both the MIT License for the code and the Gemini API's terms of service.