Gemini Image

Provides a local MCP server to generate and edit images using Google Gemini API via Claude Desktop.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "sungmin-koo-ai-geminiimagemcp": {
      "command": "/Users/yourname/GeminiImageMCP/venv/bin/python",
      "args": [
        "-m",
        "gemini_image_mcp.server"
      ],
      "env": {
        "GEMINI_API_KEY": "AIzaSy...",
        "OUTPUT_IMAGE_PATH": "/Users/yourname/Pictures/ai_generated"
      }
    }
  }
}

You can run a local Gemini Image MCP Server to generate and edit images using the Google Gemini API through a Claude Desktop client. This server handles text-to-image generation, image transformation, and automatic handling of prompts and local file storage, making it easy to integrate Gemini-powered visuals into your workflow.

How to use

Set up the MCP server, connect it to Claude Desktop, and perform image generation or transformation directly from the chat interface. You can generate new images from text prompts, transform existing images by applying new prompts, and view results inside Claude Desktop. Your generated images can also be saved to a local folder for later use.

How to install

Prerequisites you need before installing: Python 3.11 or newer, a Google Gemini API key, and Claude Desktop or another MCP-compatible client.

Step 1: Install the MCP server automatically (recommended)

# Clone the repository
git clone https://github.com/sungmin-koo-ai/GeminiImageMCP.git
cd GeminiImageMCP

# Create and activate a virtual environment
python3 -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install the package in editable mode
pip install -e .

Step 2: Verify the server starts

python -m gemini_image_mcp.server

You should see a message indicating the server started, such as “Starting Gemini Image Generator MCP server…”. Use Ctrl+C or Ctrl+Z to stop when finished.


Step 3: Configure Claude Desktop to use the MCP server

## Additional sections

Configuration and usage details are shown below. You will typically run the server locally and then connect Claude Desktop to it, either by specifying the Python path to the local environment or by using a helper command that exposes the MCP endpoint to Claude.

Environment variables you will use with the MCP server include the Gemini API key and the path where generated images should be saved locally.

## Troubleshooting

If you encounter issues connecting the MCP server to Claude Desktop or generating images, check the following: verify the server is running, confirm the Python path in your client configuration is correct, and ensure the local image output folder exists and is writable.

## Available tools

### generate\_image\_from\_text

Generates a new image from a text prompt and displays it in Claude Desktop while saving a local copy.

### transform\_image\_from\_file

Transforms an image using a provided transformation prompt, displaying the result in Claude Desktop and saving a local copy.

### transform\_image\_from\_encoded

Transforms a Base64-encoded image using a text prompt, showing the result in Claude Desktop and saving a local copy.