Gemini MCP Tool
Allows AI assistants to interact with the Google Gemini CLI, enabling large-scale analysis of files and codebases using Gemini's massive token window, natural language questions, and sandboxed code execution.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Gemini MCP Tool analyze @README.md and explain its purpose"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Gemini MCP Tool
This fork focuses on Claude Code stability while preserving the original Gemini CLI OAuth behaviour from jamubc/gemini-mcp-tool.
This is a simple Model Context Protocol (MCP) server that allows AI assistants to interact with the Gemini 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.
Authentication is handled by the installed gemini CLI. This server does not require GEMINI_API_KEY and does not call the Google GenAI SDK directly.
Ask gemini natural questions, through claude or Brainstorm new ideas in a party of 3!
TLDR:
+ 
Goal: Use Gemini's powerful analysis capabilities directly in Claude Code to save tokens and analyze large files.
Related MCP server: Gemini Code Assist MCP
Prerequisites
Before using this tool, ensure you have:
Node.js (v20.12.0 or higher)
Google Gemini CLI installed and configured
Installation
Install the published package from npm:
npm install -g @jacobcxdev/gemini-mcp-toolRegister the published package with Claude Code:
claude mcp remove gemini-cli -s user
claude mcp add gemini-cli -s user -- gemini-mcpVerify Installation
Before configuring MCP, verify the Gemini CLI OAuth path works:
gemini -p pingType /mcp inside Claude Code to verify the gemini-cli MCP is active.
Configuration
Register the MCP server with your MCP client:
{
"mcpServers": {
"gemini-cli": {
"command": "gemini-mcp"
}
}
}If your client does not resolve globally installed npm binaries, use npx instead:
{
"mcpServers": {
"gemini-cli": {
"command": "npx",
"args": [
"-y",
"@jacobcxdev/gemini-mcp-tool"
]
}
}
}Configuration File Locations:
Claude Desktop:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/claude/claude_desktop_config.json
After updating the configuration, restart your terminal session.
Stability smoke test
Run this before registering the MCP server:
npm run verifyThen test through Claude Code:
Run
/mcpand confirmgemini-cliis connected.Call
mcp__gemini-cli__ping.Call
mcp__gemini-cli__ask-geminiseveral times with short prompts.Run
/mcpagain and confirm the server stayed connected.
Example Workflow
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.
Usage Examples
With File References (using @ syntax)
ask gemini to analyze @src/main.js and explain what it doesuse gemini to summarize @. the current directoryanalyze @package.json and tell me about dependencies
General Questions (without files)
ask gemini to search for the latest tech newsuse gemini to explain div centeringask 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 dataask gemini to safely test @script.py and explain what it doesuse gemini sandbox to install numpy and create a data visualizationtest this code safely: Create a script that makes HTTP requests to an API
Tools (for the AI)
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.
sandbox-test: Safely executes code or commands in Gemini's sandbox environment. Always runs in sandbox mode.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.
Ping: A simple test tool that echoes back a message.Help: Shows the Gemini CLI help text.
Slash Commands (for the User)
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).
/sandbox: Safely tests code or scripts in Gemini's sandbox environment.
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).
/help: Displays the Gemini CLI help information.
/ping: Tests the connection to the server.
message(optional): A message to echo back.
Contributing
Contributions are welcome! Please see our Contributing Guidelines for details on how to submit pull requests, report issues, and contribute to the project.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Disclaimer: This is an unofficial, third-party tool and is not affiliated with, endorsed, or sponsored by Google.
Available Tools
6 toolsask-geminiD
model selection [-m], sandbox [-s], and changeMode:boolean for providing edits
Inputs: prompt (required), sandbox (required), changeMode (required), noFallback (required), +3 more.
brainstormA
Generate novel ideas with dynamic context gathering. --> Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement.
Inputs: prompt (required), methodology (required), ideaCount (required), includeAnalysis (required), +4 more.
fetch-chunkA
Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.
Inputs: cacheKey (required), chunkIndex (required).
HelpC
receive help information
Inputs: no named parameters.
pingC
Echo
Inputs: prompt (required).
timeout-testA
Test timeout prevention by running for a specified duration
Inputs: duration (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
All six tools have clearly distinct purposes: ask-gemini for general interaction/edits, brainstorm for creative ideation, fetch-chunk for retrieving changeMode chunks, Help for information, ping for echo, and timeout-test for testing timeouts. No overlap.
Naming is inconsistent: mix of hyphenated ('ask-gemini', 'fetch-chunk', 'timeout-test'), single words ('brainstorm', 'ping'), and capitalized ('Help'). No uniform pattern (verb-noun vs noun) or case convention.
Six tools is well-scoped for a Gemini assistant server, covering core interactions, creative generation, chunk retrieval, and utility functions like help and ping.
Covers main interaction and creativity needs, but lacks explicit conversation management or model listing tools. Minor gap in changeMode workflow documentation (fetch-chunk assumes prior partial response).
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for Google Veo AI video generation
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Related MCP Servers
- AlicenseAqualityFmaintenanceA lightweight MCP server that enables AI coding assistants to interact with Google's Gemini AI through the official CLI.3MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that integrates Google Gemini CLI with Claude Code for AI-powered development assistance, enabling code review, bug analysis, feature planning, and code explanation without requiring an API key.8MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for Google Gemini that does not require an API key, combining a CLI backend for Q\&A, research, and analysis with a web UI backend for image and video generation.4 npm3MIT
- AlicenseNot gradedqualityDmaintenanceA MCP server wrapper for Google's Gemini CLI that enables AI assistants to perform searches, have conversations, list sessions, and analyze files using Gemini's capabilities.MIT