Generate high-quality images using Google's Imagen 3.0 model via the Gemini API.
A professional Model Context Protocol (MCP) server implementation that harnesses Google's Imagen 3.0 model through the Gemini API for high-quality image generation. Built with TypeScript and designed for seamless integration with Claude Desktop and other MCP-compatible hosts.
git clone https://github.com/yourusername/gemini-imagen-mcp-server.git
cd gemini-imagen-mcp-server
npm install
npm run build
claude_desktop_config.json
:{
"mcpServers": {
"gemini-image-gen": {
"command": "node",
"args": ["./build/index.js"],
"cwd": "<path-to-project-directory>",
"env": {
"GEMINI_API_KEY": "your-gemini-api-key"
}
}
}
}
<path-to-project-directory>
: Your project pathyour-gemini-api-key
: Your Gemini API keyGenerates images using Google's Imagen 3.0 model.
Parameters:
prompt
(required): Text description of the image to generatenumberOfImages
(optional): Number of images (1-4, default: 1)File Management:
G:\image-gen3-google-mcp-server\images
{sanitized-prompt}-{timestamp}-{index}.png
Example:
Generate an image of a futuristic city at night
Creates HTML preview tags for generated images.
Parameters:
imagePaths
(required): Array of image file pathswidth
(optional): Image width in pixels (default: 512)height
(optional): Image height in pixels (default: 512)Returns HTML tags with absolute file:// URLs for local viewing.
Example:
Create HTML tags for the generated images with width=400
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run tests (when available)
npm test
Contributions are welcome! Please feel free to submit a Pull Request. For major changes:
git checkout -b feature/AmazingFeature
)git commit -m 'Add some AmazingFeature'
)git push origin feature/AmazingFeature
)The server implements two main error codes:
tool_not_found
(1): When the requested tool is not availableexecution_error
(2): When image generation or HTML creation failsMIT License - see the LICENSE file for details.
Falah G. Salieh
#MCP
#Gemini
#Imagen3
#AI
#ImageGeneration
#TypeScript
#NodeJS
#GoogleAI
#ClaudeDesktop
Made with â¤ď¸ by Falah G. Salieh
Access and interact with Harness platform data, including pipelines, repositories, logs, and artifact registries.
Integrates the Korea Meteorological Administration's public weather API to provide climate data.
Interact with MiniMax's powerful APIs for text-to-speech, voice cloning, and video/image generation.
An MCP server for Claude Code CLI that provides persistent session management, entity tracking, and context preservation across development sessions.
Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
Interact with the Monad testnet, query blockchain data, and engage with the CoinflipGame smart contract.
A Swift-based MCP server that integrates with Xcode to enhance AI development workflows.
Converts OpenAPI specifications into MCP tools, enabling AI clients to interact with external APIs seamlessly.
A specialized MCP gateway for LLM enhancement prompts and jailbreaks with dynamic schema adaptation. Provides prompts for different LLMs using an enum-based approach.
A reactive AI agent framework for creating agents that use tools to perform tasks, with support for multiple LLM providers and MCP servers.