gemini — The Intelligence Bridge

The agent that can see, hear, and imagine is the agent that cannot be outmaneuvered.

Part of FRE4X-B1TE — a monorepo of MCP servers built for autonomous agents.

Google's Gemini is not a chatbot. It is a multimodal reasoning engine. This B1TE bridges your agent directly to that engine — text, images, video, audio — so it can perceive the world as humans do, and then outthink it.

Tools

| Tool | Capability | |------|-----------| | generate_text | Text generation and reasoning via Gemini models (e.g. gemini-2.0-flash) | | analyze_media | Multimodal analysis — image, video, audio — from URL + MIME type | | generate_image | High-quality image synthesis via Imagen 3.0 / 4.0 | | generate_video | Asynchronous video generation via Veo |

Requirements

A Google AI Studio API key — set as GEMINI_API_KEY.

Deploy

{
  "mcpServers": {
    "gemini": {
      "command": "npx",
      "args": ["-y", "@fre4x/gemini"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Development

npm install
npm run dev      # tsx, no build
npm run build    # compile → dist/

License

MIT — WE ARE THE FRE4X.