MCP Gemini CLI

A Model Context Protocol (MCP) server that provides integration with Google's Gemini CLI tool.

Overview

This MCP server allows you to interact with Google's Gemini AI through the Gemini CLI tool using the Model Context Protocol. It provides a standardized interface for querying Gemini with various options and configurations.

Related MCP server: MCP Gemini API Server

Prerequisites

Node.js 18+
Google Gemini CLI tool installed and configured
MCP-compatible client (like Claude Desktop)

Installation

Clone this repository:

git clone https://github.com/kazuph/mcp-gemini-cli.git cd mcp-gemini-cli

Install dependencies:

npm install

Build the project:

npm run build

Usage

As an MCP Server

Add to your MCP client configuration (e.g., Claude Desktop):

{ "mcpServers": { "gemini-cli": { "command": "node", "args": ["/path/to/mcp-gemini-cli/dist/index.js"] } } }

Available Tools

`gemini_query`

Query Google Gemini AI with various options.

Parameters:

prompt (required): The prompt to send to Gemini
model (optional): Model to use (default: gemini-2.5-pro)
sandbox (optional): Run in sandbox mode
debug (optional): Enable debug mode
all_files (optional): Include all files in context
yolo (optional): Automatically accept all actions

Example:

{ "name": "gemini_query", "arguments": { "prompt": "Explain quantum computing in simple terms", "model": "gemini-2.5-pro", "debug": false } }

Development

Scripts

npm run build - Build the TypeScript project
npm run start - Start the MCP server
npm run dev - Start in development mode with auto-reload
npm run clean - Clean build artifacts

Project Structure

src/ ├── index.ts # Main MCP server implementation ├── ... dist/ # Compiled JavaScript output package.json # Project configuration tsconfig.json # TypeScript configuration