Gemini MCP Tool

📚View Full Documentation- Search me!, Examples, FAQ, Troubleshooting, Best Practices

This is a simple Model Context Protocol (MCP) server that allows AI assistants to interact with theGemini CLI. It enables the AI to leverage the power of Gemini's massive token window for large analysis, especially with large files and codebases using the@syntax for direction.

On2026-06-18, Google retired the Gemini CLI forfree, Google AI Pro, and Google AI Ultrausers (and individual Gemini Code Assist / GitHub-org users). Its successor is theAntigravity CLI(agy). SeeGoogle's announcement.

curl -fsSL https://antigravity.google/cli/install.sh | bash # macOS / Linux

Theagybackend isexperimental: print mode is Gemini 3.5 Flash-only, replies come fromagy's stdout (transcript recovery only as a fallback), and tool execution isn't sandboxed in-p. The tool emits a notice when a requestedmodel/sandboxcan't be honored, and surfacesagy's own errors (quota, auth) verbatim. Full analysis:docs/migration/antigravity-cli.md.

Before using this tool, ensure you have:
- Node.js(v16.0.0 or higher)
- Google Gemini CLIinstalled and configured

claude mcp add gemini-cli -- npx -y gemini-mcp-tool

claude mcp add gemini-cli -- npx -- y gemini-mcp-tool

"gemini-cli": { "command": "npx", "args": ["-y", "gemini-mcp-tool"] }

Register the MCP server with your MCP client:

Add this configuration to your Claude Desktop config file:

{ "mcpServers": { "gemini-cli": { "command": "npx", "args": ["-y", "gemini-mcp-tool"] } } }

If you installed globally, use this configuration instead:

{ "mcpServers": { "gemini-cli": { "command": "gemini-mcp" } } }

- Claude Desktop:

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

After updating the configuration, restart your terminal session.

- Natural language: "use gemini to explain index.html", "understand the massive project using gemini", "ask gemini to search for latest news"
- Claude Code: Type/gemini-cliand commands will populate in Claude Code's interface.

- ask gemini to analyze @src/main.js and explain what it does
- use gemini to summarize @. the current directory
- analyze @package.json and tell me about dependencies

- ask gemini to search for the latest tech news
- use gemini to explain div centering
- ask gemini about best practices for React development related to @file_im_confused_about

Using Gemini CLI's Sandbox Mode (-s)

The sandbox mode allows you to safely test code changes, run scripts, or execute potentially risky operations in an isolated environment.

- use gemini sandbox to create and run a Python script that processes data
- ask gemini to safely test @script.py and explain what it does
- use gemini sandbox to install numpy and create a data visualization
- test this code safely: Create a script that makes HTTP requests to an API

These tools are designed to be used by the AI assistant.

- ask-gemini: Asks Google Gemini for its perspective. Can be used for general questions or complex analysis of files.

- prompt(required): The analysis request. Use the@syntax to include file or directory references (e.g.,@src/main.js explain this code) or ask general questions (e.g.,Please use a web search to find the latest news stories).
- model(optional): The Gemini model to use. Defaults togemini-2.5-pro.
- sandbox(optional): Set totrueto run in sandbox mode for safe code execution.

- prompt(required): Code testing request (e.g.,Create and run a Python script that...or@script.py Run this safely).
- model(optional): The Gemini model to use.

You can use these commands directly in Claude Code's interface (compatibility with other clients has not been tested).

- /analyze: Analyzes files or directories using Gemini, or asks general questions.

- prompt(required): The analysis prompt. Use@syntax to include files (e.g.,/analyze prompt:@src/ summarize this directory) or ask general questions (e.g.,/analyze prompt:Please use a web search to find the latest news stories).

- prompt(required): Code testing request (e.g.,/sandbox prompt:Create and run a Python script that processes CSV dataor/sandbox prompt:@script.py Test this script safely).

- message(optional): A message to echo back.

Contributions are welcome! Please see ourContributing Guidelinesfor details on how to submit pull requests, report issues, and contribute to the project.

This project is licensed under the MIT License. See theLICENSEfile for details.

next-devtools-mcp is a MCP server that provides Next.js development tools and utilities for AI coding assistants like Claude and Cursor.