Package Exports

gemini-imagen4-mcp
gemini-imagen4-mcp/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (gemini-imagen4-mcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Gemini Imagen 4.0 MCP Server

A Model Context Protocol (MCP) server that provides image generation capabilities using Google's Imagen 4.0 models.

Features

Generate high-quality images from text descriptions
Support for multiple Imagen 4.0 model variants:
- imagen-4.0-generate-preview-06-06 (default)
- imagen-4.0-fast-generate-preview-06-06
- imagen-4.0-ultra-generate-preview-06-06
Configurable aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9)
Multiple output formats (PNG, JPEG)
Content filtering with detailed feedback
Automatic file saving with timestamped filenames

Installation

npm install -g gemini-imagen4-mcp

Setup

Get a Gemini API key from Google AI Studio

Set the environment variable:

export GEMINI_API_KEY="your-api-key-here"

Usage with Claude Desktop

Add this server to your Claude Desktop configuration:

{
  "mcpServers": {
    "gemini-imagen4": {
      "command": "gemini-imagen4-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

generate_image_from_text

Generate an image from a text description.

Parameters:

prompt (required): Text description of the image to generate
model (optional): Imagen 4.0 model variant to use
- imagen-4.0-generate-preview-06-06 (default)
- imagen-4.0-fast-generate-preview-06-06
- imagen-4.0-ultra-generate-preview-06-06
aspectRatio (optional): Aspect ratio of the generated image
- 1:1, 3:4, 4:3, 9:16, 16:9
outputMimeType (optional): Output format (image/png or image/jpeg, default: image/png)

Example:

Generate an image of "a serene mountain lake at sunset with reflection"

Generated images are automatically saved to a generated-images/ directory with timestamped filenames.

Development

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

License

MIT