Gemini Imagen 3.0 MCP Server

What is Gemini Imagen 3.0 MCP Server?

A professional Model Context Protocol (MCP) server that uses Google's Imagen 3.0 model via the Gemini API for high-quality image generation. Built with TypeScript, it integrates with Claude Desktop and other MCP-compatible hosts.

How to use Gemini Imagen 3.0 MCP Server?

Install Node.js 18+, clone the repository, run npm install and npm run build. Configure Claude Desktop by adding the server to claude_desktop_config.json with your Gemini API key as the GEMINI_API_KEY environment variable. The server provides two tools: generate_images (requires a prompt; optional numberOfImages from 1-4) and create_image_html (requires imagePaths; optional width and height).

Key features of Gemini Imagen 3.0 MCP Server

• Generates up to 4 high-quality images per request
• Automatic file management with intelligent naming
• HTML preview generation using file:// protocol
• MCP protocol for AI agent compatibility
• TypeScript implementation with robust error handling

Use cases of Gemini Imagen 3.0 MCP Server

• Generate images from text prompts using Imagen 3.0
• Create HTML preview tags for local viewing of generated images
• Automate image creation workflows in MCP-compatible environments

FAQ from Gemini Imagen 3.0 MCP Server

What are the prerequisites for using this server?

Node.js 18 or higher, a Google Gemini API key, and Claude Desktop or another MCP-compatible host.

How do I configure the server for Claude Desktop?

Add the server configuration to claude_desktop_config.json with the command node, arguments ./build/index.js, and the environment variable GEMINI_API_KEY.

What tools does the server provide?

generate_images for image generation and create_image_html for creating HTML preview tags. Both have required and optional parameters as documented.

Where are generated images saved?

Images are automatically saved in G:\image-gen3-google-mcp-server\images with filenames following the pattern {sanitized-prompt}-{timestamp}-{index}.png.

What error codes does the server use?

tool_not_found (1) when the requested tool is unavailable, and execution_error (2) when image generation or HTML creation fails.