Gemini Collaboration

You can run a Gemini collaboration MCP server to get a second opinion from Gemini or to collaborate on code iteratively. Set up a local or npm-backed MCP server, connect it to your Claude Code client, and use dedicated commands to consult Gemini or collaborate on code projects.

How to use

You will use two core commands in your MCP client to interact with Gemini. First, ask for a second opinion on your approach or code by selecting the consult Gemini actions. Second, collaborate on code by starting a joint build session where you and Gemini refine requirements, decide on the tech stack, and generate code through guided dialogue.

How to install

Prerequisites you need before installing: Node.js 18 or higher, a Gemini API key, and access to Claude Code (Anthropic's official CLI). Ensure you have npm installed as part of Node.js.

# Install the MCP server globally (recommended)
npm install -g gemini-collaboration-mcp

# Or, install locally by cloning the repository
# git clone https://github.com/henry2craftman/gemini-collaboration-mcp.git
# cd gemini-collaboration-mcp
# npm install
# npm run build

Configuration

Obtain your Gemini API key from Gemini AI Studio. Then configure Claude Code to load the MCP server with the API key in the environment.

{
  "mcpServers": {
    "gemini_collaboration": {
      "command": "npx",
      "args": ["-y", "gemini-collaboration-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      }
    }
  }
}

Usage notes

If you installed the MCP server via npm, the above configuration enables you to run the MCP server through npx when Claude Code loads its settings. If you install locally, point Claude Code to the local runtime so the MCP server starts from the built distribution.

Examples of commands you will run in Claude Code

Consult Gemini examples you can try in your editor:

• Gemini, what do you think about this approach?
• Ask Gemini to review this code
• Get Gemini's opinion on this implementation.

Collaborate on code examples you can try in your editor:

• Collaborate with Gemini to build a 3D dice game
• Work with Gemini to create a calculator app
• Develop a todo list app together with Gemini.

Architecture

This MCP server uses the AI Orchestration Framework to chain AI model interactions, manage context between Claude and Gemini, and execute multi-step collaborative workflows.

Security and credentials

Keep your Gemini API key secure. Do not commit secrets to source control. Use environment variable management to load GEMINI_API_KEY when starting the MCP server.

Development

To contribute, install dependencies, build, and run tests or start the MCP server locally.

# Install dependencies
npm install

# Build the MCP server
npm run build

# Run MCP server directly (for development)
npm run mcp

# Run interactive chat (optional)
npm run chat

License

MIT

Contributing

Contributions are welcome. Please open an issue or submit a pull request.

Support

For issues, questions, or suggestions, please open an issue on the project's issue tracker.

Available tools

consult_gemini

Request Gemini's second opinion, code reviews, validation, or fresh perspectives on your approach or implementation.

collaborate_on_code

Partner with Gemini to create and refine code through an iterative, dialogue-based workflow starting from product requirements.