Gemini
A bridge that connects the Model Context Protocol to the Gemini CLI via the Agent Client Protocol (ACP) for high-performance, stateful AI interactions. It enables MCP clients to leverage Gemini's autonomous capabilities, including multi-modal support
What is Gemini?
Gemini is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to bridge that connects the model context protocol to the gemini cli via the agent client protocol (acp) for high-performance, stateful ai interactions. it enables mcp clients to leverage gemini's autono...
A bridge that connects the Model Context Protocol to the Gemini CLI via the Agent Client Protocol (ACP) for high-performance, stateful AI interactions. It enables MCP clients to leverage Gemini's autonomous capabilities, including multi-modal support
This server falls under the APIs and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A bridge that connects the Model Context Protocol to the Gem
Use Cases
Maintainer
Works with
Installation
NPM
npx -y geminiManual Installation
npx -y geminiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Gemini
Gemini MCP is a bridge that connects MCP clients like Claude Code to the Gemini CLI via the Agent Client Protocol (ACP), enabling stateful, high-performance interactions with Google's Gemini models directly from within your MCP workflow. Unlike a simple API wrapper, it maintains long-lived ACP sessions per workspace to eliminate cold-start overhead, and supports multi-modal inputs including vision analysis via image paths. Developers use it to leverage Gemini's autonomous coding capabilities — including its own tool use — as a parallel AI engine alongside their primary MCP client.
Prerequisites
- Python 3.12 or higher installed
- uv package manager installed (https://docs.astral.sh/uv/)
- Gemini CLI installed: npm install -g @google/gemini-cli
- A Google account authenticated with the Gemini CLI (run gemini in a terminal to complete auth)
- An MCP-compatible client such as Claude Code or Claude Desktop
Install the Gemini CLI
Install the official Gemini CLI from npm. This is the underlying engine that gemini_mcp communicates with via ACP.
npm install -g @google/gemini-cliAuthenticate the Gemini CLI
Run gemini in your terminal to complete the Google authentication flow. This stores credentials that the MCP server uses for all subsequent Gemini requests.
geminiInstall gemini_mcp via uvx (recommended for Claude Code)
Use the Claude Code CLI to add the server directly. uvx pulls and runs the package from GitHub on demand — no separate install step needed.
claude mcp add gemini -s user --transport stdio -- uvx --from git+https://github.com/shenyunhuan/gemini_mcp.git geminimcpAlternative: install manually with uv
If you prefer a persistent install, use uv tool install then add the server to your MCP client manually.
uv tool install --from git+https://github.com/shenyunhuan/gemini_mcp.git geminimcp
claude mcp add gemini -s user --transport stdio -- geminimcpVerify the connection
In your MCP client, ask to list available Gemini models or sessions to confirm the bridge is connected and the ACP process started successfully.
Gemini Examples
Client configuration
Claude Desktop JSON config using uvx to run gemini_mcp directly from the GitHub repository.
{
"mcpServers": {
"gemini": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/shenyunhuan/gemini_mcp.git",
"geminimcp"
]
}
}
}Prompts to try
Example prompts that leverage the Gemini bridge from within Claude Code or Claude Desktop.
- "Use Gemini to analyze the architecture of this codebase at /Users/me/projects/app"
- "Ask Gemini to review and suggest improvements for this function"
- "Use Gemini with vision to describe the UI in /tmp/screenshot.png"
- "List active Gemini ACP sessions"
- "Reset the Gemini session for my current workspace"
- "Switch to gemini-3.1-flash for a quick code review to reduce latency"Troubleshooting Gemini
Error: Gemini CLI not found or ACP process fails to start
Verify the Gemini CLI is installed and on your PATH: run gemini --version in a terminal. If it is not found, run npm install -g @google/gemini-cli and ensure your npm global bin directory is in your PATH.
Authentication error when calling the gemini tool
Run gemini in an interactive terminal to re-authenticate with your Google account. The Gemini CLI stores credentials locally and the MCP server reuses them — if they expire, re-running the interactive auth flow refreshes them.
uvx command not found when adding the MCP server
Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh, then restart your terminal. uv includes uvx as a companion command for running Python tools without permanent installation.
Frequently Asked Questions about Gemini
What is Gemini?
Gemini is a Model Context Protocol (MCP) server that bridge that connects the model context protocol to the gemini cli via the agent client protocol (acp) for high-performance, stateful ai interactions. it enables mcp clients to leverage gemini's autonomous capabilities, including multi-modal support It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Gemini?
Install via npm with the command: npx -y gemini. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Gemini?
Gemini works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Gemini free to use?
Yes, Gemini is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Gemini Alternatives — Similar APIs Servers
Looking for alternatives to Gemini? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
Browse More APIs MCP Servers
Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Gemini in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Gemini?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.