home / mcp / gemini mcp server
A Model Context Protocol (MCP) server that integrates with Google's Gemini Pro model, can be used in Claude Desktop App.
Configuration
View docs{
"mcpServers": {
"georgejeffers-gemini-mcp-server": {
"command": "node",
"args": [
"dist/gemini_mcp_server.js"
],
"env": {
"GEMINI_API_KEY": "YOUR_API_KEY"
}
}
}
}You can run a Gemini-based MCP server that exposes the Gemini Pro model to your MCP clients, including Claude Desktop. This server lets you process prompts through Gemini and return structured results to your client apps, enabling seamless integration of Gemini’s capabilities into your workflows.
You will run the MCP server locally or remotely and connect your MCP client to it. Start the server with Node, then point your client to the local process. The server accepts requests from your client, runs Gemini against your prompts, and returns model outputs. You can use it to generate text, analyze prompts, and handle long-running interactions by leveraging Gemini Pro through a stable MCP interface.
Prerequisites you need before installation include Node.js 18 or higher, a Google Gemini API key, TypeScript tooling, and a Claude Desktop app if you plan to integrate with Claude.
# Prerequisites
node -v
# Install dependencies
npm install
# Build the project
npm run buildIf you plan to run and connect via Claude Desktop, you will configure Claude to launch the MCP server as a local stdio process and supply your Gemini API key through an environment variable.
{
"name": "gemini",
"command": "node",
"args": ["dist/gemini_mcp_server.js"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
},
"cwd": "/path/to/mcp-gemini-server"
}Keep your Gemini API key secure. Do not commit keys to source control. Rotate keys periodically and restrict access to the MCP server only to trusted clients.
Generates text using the Gemini MCP server, exposing the server-side Gemini model to clients.