Gemini MCP
Gemini-MCP is an MCP server that encapsulates Google's Gemini CLI tool into a standard MCP protocol interface, enabling Claude Code to invoke Gemini for AI-assisted programming tasks.
What is Gemini MCP?
Gemini MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to gemini-mcp is an mcp server that encapsulates google's gemini cli tool into a standard mcp protocol interface, enabling claude code to invoke gemini for ai-assisted programming tasks.
Gemini-MCP is an MCP server that encapsulates Google's Gemini CLI tool into a standard MCP protocol interface, enabling Claude Code to invoke Gemini for AI-assisted programming tasks.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Gemini-MCP is an MCP server that encapsulates Google's Gemin
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx geminimcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Gemini MCP
GeminiMCP is an MCP server that wraps Google's Gemini CLI tool and exposes it as a standard MCP tool, allowing Claude Code to delegate tasks to Gemini and compare or combine outputs from both AI models. It enables multi-turn conversations with Gemini directly from within Claude's coding workflow, making it useful for second-opinion code reviews, large-context tasks where Gemini excels, and AI-assisted programming that benefits from cross-model collaboration. The server communicates over stdio and is installed via the `uvx` tool runner, requiring no separate package installation step.
Prerequisites
- Claude Code installed and configured on your machine
- Google Gemini CLI installed and authenticated (run `gemini` in terminal to verify)
- uv package manager installed (https://astral.sh/uv)
- Python 3.8+ available on your system
- An MCP-compatible client such as Claude Code or Claude Desktop
Install uv package manager
GeminiMCP is installed via uvx, which ships with the uv package manager. Install uv first if you don't have it.
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Verify Gemini CLI is configured
GeminiMCP wraps the Gemini CLI, so that CLI must be installed and authenticated before the MCP server will work. Run `gemini` in your terminal to confirm it is present and authenticated with your Google account.
gemini --versionAdd GeminiMCP to Claude Code
Use the `claude mcp add` command to register the GeminiMCP server. This installs the server from GitHub using uvx and makes it available as a user-scoped MCP server named `gemini`.
claude mcp add gemini -s user --transport stdio -- uvx --from git+https://github.com/GuDaStudio/geminimcp.git geminimcpVerify the server is registered
Confirm GeminiMCP appears in your list of active MCP servers and that Claude Code can see the `gemini` tool.
claude mcp listAuto-approve the gemini tool (optional)
To avoid approval prompts every time the gemini tool is invoked, add it to the allow list in your Claude settings file at ~/.claude/settings.json.
{
"allow": [
"mcp__gemini__gemini"
]
}Configure Claude to collaborate with Gemini (optional)
For best results, add a prompt in ~/.claude/CLAUDE.md instructing Claude when to delegate tasks to Gemini. This unlocks true cross-model collaboration during coding sessions.
Gemini MCP Examples
Client configuration
GeminiMCP is added via the claude CLI command rather than a config file, but the equivalent JSON config for Claude Desktop is shown below.
{
"mcpServers": {
"gemini": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/GuDaStudio/geminimcp.git",
"geminimcp"
]
}
}
}Prompts to try
Once configured, use these prompts in Claude Code to delegate tasks to Gemini.
- "Use Gemini to review this function and tell me if you agree with its assessment"
- "Ask Gemini to generate a unit test suite for the selected code"
- "Get Gemini's opinion on this architecture design, then compare it with yours"
- "Use Gemini with SESSION_ID 'refactor-001' to maintain context across this refactoring task"Troubleshooting Gemini MCP
Error: 'gemini' command not found when the MCP server starts
The Gemini CLI must be installed and on your PATH before GeminiMCP can use it. Install it from the official Google Gemini CLI page and run `gemini` in your terminal to authenticate.
uvx fails to install the package from GitHub
Ensure you have uv installed and that your internet connection can reach GitHub. Try running the uvx command manually: `uvx --from git+https://github.com/GuDaStudio/geminimcp.git geminimcp --help` to diagnose the error.
Claude keeps asking for approval before calling the gemini tool
Add `mcp__gemini__gemini` to the `allow` array in ~/.claude/settings.json to auto-approve invocations without manual confirmation each time.
Frequently Asked Questions about Gemini MCP
What is Gemini MCP?
Gemini MCP is a Model Context Protocol (MCP) server that gemini-mcp is an mcp server that encapsulates google's gemini cli tool into a standard mcp protocol interface, enabling claude code to invoke gemini for ai-assisted programming tasks. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Gemini MCP?
Follow the installation instructions on the Gemini MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Gemini MCP?
Gemini MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Gemini MCP free to use?
Yes, Gemini MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Gemini MCP Alternatives — Similar Coding Agents Servers
Looking for alternatives to Gemini MCP? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Gemini MCP 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 MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.