Use This MCP server To

Integrate Gemini AI models with Claude Desktop Stream real-time AI responses from Gemini models Securely manage Gemini API keys in MCP workflows Customize Gemini model parameters for tailored outputs Enable multi-model workflows combining Gemini and other LLMs

README

Gemini MCP Server

Model Context Protocol (MCP) server implementation that enables Claude Desktop to interact with Google's Gemini AI models.

Features

Full MCP protocol support
Real-time response streaming
Secure API key handling
Configurable model parameters
TypeScript implementation

Quick Start

Get Gemini API Key
- Visit Google AI Studio
- Create a new API key

Configure Claude Desktop

Locate your config file:

Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Add Gemini configuration:

{
  "mcpServers": {
    "gemini": {
      "command": "npx",
      "args": ["-y", "github:aliargun/mcp-server-gemini"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop

Documentation

Claude Desktop Setup Guide - Detailed setup instructions
Examples and Usage - Usage examples and advanced configuration
Implementation Notes - Technical implementation details
Development Guide - Guide for developers
Troubleshooting Guide - Common issues and solutions

Local Development

# Clone repository
git clone https://github.com/aliargun/mcp-server-gemini.git
cd mcp-server-gemini

# Install dependencies
npm install

# Start development server
npm run dev

Contributing

Contributions are welcome! Please see our Contributing Guide.

Common Issues

Connection Issues
- Check if port 3005 is available
- Verify internet connection
- See Troubleshooting Guide
API Key Problems
- Verify API key is correct
- Check permissions
- See Setup Guide

Security

API keys are handled via environment variables only
No sensitive data is logged or stored
Regular security updates

License

MIT

mcp-server-gemini FAQ

How do I obtain an API key for the Gemini MCP server?

You can get a Gemini API key by visiting Google AI Studio at https://makersuite.google.com/app/apikey and creating a new API key.

How is the Gemini API key secured in the MCP server?

The server securely handles API keys through environment variables, preventing exposure in code or logs.

What programming language is the mcp-server-gemini implemented in?

It is implemented in TypeScript, ensuring type safety and maintainability.

Can I configure model parameters for Gemini through this MCP server?

Yes, the server supports configurable model parameters to customize AI responses.

Does the server support real-time response streaming?

Yes, it supports real-time streaming of responses from Gemini models for interactive applications.

How do I configure Claude Desktop to use the Gemini MCP server?

Add the Gemini server configuration to Claude Desktop's config file with the appropriate command, args, and environment variables as documented.

Is the mcp-server-gemini compatible with other LLM providers?

While focused on Gemini, MCP's provider-agnostic design allows integration alongside models from OpenAI, Anthropic Claude, and others.

Where can I find the source code for the Gemini MCP server?

The source code is available on GitHub at the repository aliargun/mcp-server-gemini.