This MCP server lets you generate and transform images using Google's Gemini model through a simple interface that works with any MCP client. It handles text-to-image conversion, intelligent filename creation, and local image storage automatically.
Clone the repository:
git clone https://github.com/your-username/gemini-image-generator.git
cd gemini-image-generator
Create a virtual environment and install dependencies:
# Using regular venv
python -m venv .venv
source .venv/bin/activate
pip install -e .
# Or using uv
uv venv
source .venv/bin/activate
uv pip install -e .
Copy the example environment file and add your API key:
cp .env.example .env
Edit the .env
file to include your Google Gemini API key and preferred output path:
GEMINI_API_KEY="your-gemini-api-key-here"
OUTPUT_IMAGE_PATH="/path/to/save/images"
Add the following to your claude_desktop_config.json
:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"gemini-image-generator": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/gemini-image-generator",
"run",
"server.py"
],
"env": {
"GEMINI_API_KEY": "GEMINI_API_KEY",
"OUTPUT_IMAGE_PATH": "OUTPUT_IMAGE_PATH"
}
}
}
}
Once installed and configured, you can ask Claude to generate or transform images using prompts.
Creates a new image from a text prompt description.
generate_image_from_text(prompt: str) -> Tuple[bytes, str]
Parameters:
prompt
: Text description of the image you want to generateReturns:
Example prompts:
Transforms an existing image based on a text prompt using base64-encoded image data.
transform_image_from_encoded(encoded_image: str, prompt: str) -> Tuple[bytes, str]
Parameters:
encoded_image
: Base64 encoded image data with format header (must be in format: "data:image/[format];base64,[data]")prompt
: Text description of how you want to transform the imageReturns:
Example prompts:
Transforms an existing image file based on a text prompt.
transform_image_from_file(image_file_path: str, prompt: str) -> Tuple[bytes, str]
Parameters:
image_file_path
: Path to the image file to be transformedprompt
: Text description of how you want to transform the imageReturns:
Example prompts:
To generate a new image:
To transform existing images:
The generated/transformed images will be saved to your configured output path and displayed in Claude.
You can test the application by running the FastMCP development server:
fastmcp dev server.py
This command starts a local development server and makes the MCP Inspector available at http://localhost:5173/. The inspector provides a web interface where you can test the image generation tools without needing to use Claude or another MCP client.
When using this MCP server with Claude Desktop Host:
Performance Issues: Using transform_image_from_encoded
may take significantly longer to process compared to other methods due to the overhead of transferring large base64-encoded image data.
Path Resolution Problems: There may be issues with correctly resolving image paths when using Claude Desktop Host.
For the best experience, consider using alternative MCP clients or the transform_image_from_file
method when possible.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.