🎨 Gemini-Imagen4

Local AI Image Generation MCP Server powered by Google's Imagen 4.0 models

Generate stunning images from text descriptions using Google's cutting-edge Imagen 4.0 models through the Model Context Protocol (MCP). Images are saved locally to ./generated-images/ directory.

✨ Features

• 🖼️ High-quality image generation using Google's latest Imagen 4.0 models

• ⚡ Multiple model variants for different speed/quality needs

• 🎯 Flexible aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9)

• 📸 Multiple output formats (PNG, JPEG)

• 🔒 Built-in safety filtering with reason reporting

• 💾 Local file storage - images saved to ./generated-images/ directory

• 🚀 Easy local setup - run with npx or npm

• 🔌 MCP Resources - browse generated images via MCP protocol

🚀 Quick Start

Prerequisites

• Node.js 18+

• Google Gemini API key (Get one here)

Installation & Usage

Option 1: Install from npm (Recommended)

Then run:

Option 2: Run directly with npx

Option 3: Clone and run locally

You'll be prompted to enter your Gemini API key when you first run it.

Usage

Once running, the server provides:

Tool: generate_image_from_text

Generate images from text descriptions with optional customization.

Parameters:

• prompt (required): Text description of the image to generate

• model (optional): Choose from:

  • imagen-4.0-generate-preview-06-06 (default - balanced)

  • imagen-4.0-fast-generate-preview-06-06 (faster generation)

  • imagen-4.0-ultra-generate-preview-06-06 (highest quality)

• aspectRatio (optional): 1:1, 3:4, 4:3, 9:16, or 16:9

• outputMimeType (optional): image/png (default) or image/jpeg

Example:

Response: Images are saved to ./generated-images/ with timestamped filenames like 1754998591_majestic_dragon_soaring.png

Resource: generated-images

Browse the generated images directory via MCP resources protocol.

🔌 Adding to Claude Desktop

To use this server with Claude Desktop, add it to your MCP configuration:

Edit your

Replace your-api-key-here with your actual Gemini API key, then restart Claude Desktop.

🔧 Configuration

The server requires a Gemini API key and supports the following configuration:

🏃‍♂️ Development

Run the development server:

📦 Model Variants

• Standard (imagen-4.0-generate-preview-06-06): Best balance of quality and speed

• Fast (imagen-4.0-fast-generate-preview-06-06): Optimized for quick generation

• Ultra (imagen-4.0-ultra-generate-preview-06-06): Maximum quality output

🛡️ Safety & Content Filtering

All images are processed through Google's built-in safety filters. If content is filtered, the tool will return the reason for filtering instead of an image.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

MIT License - see LICENSE file for details.

🔗 Links

• Google AI Studio

• Model Context Protocol

• Smithery Platform

Built with ❤️ using Google's Imagen 4.0 and the Model Context Protocol