Gemini MCP Server
@MCP-Mirror
About Gemini MCP Server
Mirror of
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"gemini": {
"command": "npx",
"args": [
"-y",
"github:aliargun/mcp-server-gemini"
],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Gemini MCP Server?
Gemini MCP Server is a Model Context Protocol (MCP) server that enables Claude Desktop to interact with Google's Gemini AI models. It provides full MCP protocol support with real‑time response streaming and secure API key handling.
How to use Gemini MCP Server?
Obtain a Gemini API key from Google AI Studio, then configure Claude Desktop by adding the server to claude_desktop_config.json (location varies by OS) with the command npx -y github:aliargun/mcp-server-gemini and the environment variable GEMINI_API_KEY. Restart Claude Desktop to start using it. For local development, clone the repository, run npm install, and start with npm run dev.
Key features of Gemini MCP Server
- Full MCP protocol support
- Real‑time response streaming
- Secure API key handling via environment variables
- Configurable model parameters
- TypeScript implementation
- Available as an npx one‑line command
Use cases of Gemini MCP Server
- Use Google Gemini AI models directly inside Claude Desktop
- Stream real‑time responses from Gemini for conversational tasks
- Develop and test MCP server integrations locally
- Securely manage API keys without exposing them in config files
FAQ from Gemini MCP Server
How do I get a Gemini API key?
Visit Google AI Studio (makersuite.google.com/app/apikey) and create a new API key.
Where is the Claude Desktop configuration file?
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows: %APPDATA%\Claude\claude_desktop_config.json. On Linux: ~/.config/Claude/claude_desktop_config.json.
What should I do if I encounter connection issues?
Check that port 3005 is available, verify your internet connection, and consult the Troubleshooting Guide in the repository.
How does the server handle API keys?
API keys are passed exclusively through the GEMINI_API_KEY environment variable; no sensitive data is logged or stored.
What runtime requirements does the server have?
It requires Node.js and npm/npx. The server is written in TypeScript and runs with the provided npx command or after local npm install.
Frequently asked questions
How do I get a Gemini API key?
Visit Google AI Studio (makersuite.google.com/app/apikey) and create a new API key.
Where is the Claude Desktop configuration file?
On macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`. On Windows: `%APPDATA%\Claude\claude_desktop_config.json`. On Linux: `~/.config/Claude/claude_desktop_config.json`.
What should I do if I encounter connection issues?
Check that port 3005 is available, verify your internet connection, and consult the Troubleshooting Guide in the repository.
How does the server handle API keys?
API keys are passed exclusively through the `GEMINI_API_KEY` environment variable; no sensitive data is logged or stored.
What runtime requirements does the server have?
It requires Node.js and npm/npx. The server is written in TypeScript and runs with the provided npx command or after local `npm install`.
Basic information
More AI & Agents MCP servers
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
Comments