Gemini MCP Server

🚀 Gemimi MCP Server (in Python)

A Model Context Protocol (MCP) server for Gemimi integration, built on FastMCP.

This server is implemented in Python using the fastmcp library, offering seamless integration with Gemimi services.

🚀 Quick Start

Build the Docker Image

To get started, build the Docker image for the Gemimi MCP server. Run the following command in your terminal:

docker build -t gemini-mcp-server .

💻 Usage Examples

Integration with Cursor/Claude

To integrate the Gemimi MCP server with Cursor or Claude, follow these steps:

1. Navigate to MCP Settings and select Add MCP server.
2. Add the following configuration:

{
  "mcpServers": {
    "gemini": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--network",
        "host",
        "-e",
        "GEMINI_API_KEY",
        "-e",
        "GEMINI_MODEL",
        "-e",
        "GEMINI_BASE_URL",
        "-e",
        "HTTP_PROXY",
        "-e",
        "HTTPS_PROXY",
        "gemini-mcp-server:latest"
      ],
      "env": {
        "GEMINI_API_KEY":"your_api_key_here",
        "GEMINI_MODEL":"gemini-2.5-flash",
        "GEMINI_BASE_URL":"https://generativelanguage.googleapis.com/v1beta/openai/",
        "HTTP_PROXY":"http://127.0.0.1:17890",
        "HTTPS_PROXY":"http://127.0.0.1:17890"
      }
    }
  }
}

⚠️ Important Note

Don't forget to replace the values of GEMINI_API_KEY, GEMINI_MODEL, GEMINI_BASE_URL, HTTP_PROXY, and HTTPS_PROXY with your actual Gemimi credentials and instance URL.