Gemini Gen MCP

Using in llms .py

Paste server configuration into llms .py MCP Servers:

Name: gemini-gen

{
  "description": "Gemini Image and Audio TTS generation",
  "command": "uvx",
  "args": [
    "gemini-gen-mcp"
  ],
  "env": {
    "GEMINI_API_KEY": "$GEMINI_API_KEY"
  }
}

You can either edit the mcp.json file directly to add your own servers or use the UI to Add, Edit, or Delete servers or use the Copy button to copy an individual server's configuration.

Using with Claude Desktop

Add this to your or claude_desktop_config.json:

{
  "mcpServers": {
    "gemini-gen": {
      "description": "Gemini Image and Audio TTS generation",
      "command": "uvx",
      "args": [
        "gemini-gen-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "$GEMINI_API_KEY"
      }
    }
  }
}

Development Server

For development, you can run this server using uv:

{
  "mcpServers": {
    {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/ServiceStack/gemini-gen-mcp",
        "gemini-gen-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "$GEMINI_API_KEY"
      }
    }
  }
}

Features

This MCP server provides tools to:

• Generate images from text using Gemini's Flash Image model
• Generate audio from text using Gemini 2.5 Flash Preview TTS model

Results

Upon execution, the tool's output is displayed in a results dialog with specific rendering based on the output type:

When included, the same tools can be also be invoked indirectly by LLMs during chat sessions:

Prerequisites

You need a Google Gemini API key to use this server. Get one from Google AI Studio.

Environment Variables

Set the environment variables:

export GEMINI_API_KEY='your-api-key-here'
export GEMINI_DOWNLOAD_PATH='/path/to/downloads'  # optional

Generated files are organized by type and date:

• Images: $GEMINI_DOWNLOAD_PATH/images/YYYY-MM-DD/
• Audio: $GEMINI_DOWNLOAD_PATH/audios/YYYY-MM-DD/

Each generated file includes a companion .info.json file with generation metadata.

Usage

Running the Server

Run the MCP server directly:

gemini-gen-mcp

Or as a Python module:

python -m gemini_gen_mcp.server

Available Tools

text_to_image

Generate images from text using Gemini's Flash (Nano Banana) Image models.

@mcp.tool()
async def text_to_image(
    prompt: Annotated[str, "Text description of the image to generate"],
    model: ImageModels = ImageModels.NANO_BANANA,
    aspect_ratio: AspectRatio = AspectRatio.SQUARE,
    temperature: Annotated[
        float, "Sampling temperature for image generation (default: 1.0)"
    ] = 1.0,
    top_p: Annotated[
        Optional[float], "Nucleus sampling parameter for image generation (optional)"
    ] = None,
) -> Image

Parameters:

• prompt (string, required): Text description of the image to generate
• model (string, optional): Gemini model to use
  • gemini-2.5-flash-image (default)
  • gemini-3-pro-image-preview
• aspect_ratio (string, optional): Aspect ratio for the generated image (default: "1:1")
  • Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
• temperature (float, optional): Sampling temperature for image generation (default: 1.0)
• top_p (float, optional): Nucleus sampling parameter (optional)

Example:

{
  "prompt": "A serene mountain landscape at sunset with a lake",
  "model": "gemini-2.5-flash-image",
  "aspect_ratio": "16:9",
  "temperature": 1.0
}

text_to_audio

Generate speech audio from text using Gemini Flash TTS model. Output is saved as WAV format.

@mcp.tool()
async def text_to_speech(
    text: Annotated[str, "Text to convert to speech"],
    model: AudioModels = AudioModels.GEMINI_2_5_FLASH_PREVIEW_TTS,
    voice: VoiceName = VoiceName.KORE,
) -> Audio

Parameters:

• text (string, required): Text to convert to speech
• model (string, optional): Gemini TTS model to use
  • gemini-2.5-flash-preview-tts (default)
  • gemini-2.5-pro-preview-tts
• voice (string, optional): Voice to use for speech generation (default: "Kore")

Available Voices:

Example:

{
  "text": "Hello, this is a test of the Gemini text to speech system.",
  "model": "gemini-2.5-flash-preview-tts",
  "voice": "Kore"
}