Claude Image Gen
AI-powered image generation using Google Gemini, integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
What is Claude Image Gen?
Claude Image Gen is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-powered image generation using google gemini, integrated with claude code via skills or claude.ai via mcp (model context protocol).
AI-powered image generation using Google Gemini, integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI-powered image generation using Google Gemini, integrated
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx claude-image-genConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Claude Image Gen
Claude Image Gen is an MCP server that integrates Google Gemini's image generation capabilities directly into Claude Code and Claude Desktop. It exposes a `create_asset` tool that lets AI assistants generate images from text prompts, saving them to disk and returning file paths. Developers use it to automate image creation for websites, presentations, and marketing assets without leaving their AI coding workflow.
Prerequisites
- Node.js 18 or higher installed
- A Google Gemini API key from https://aistudio.google.com/apikey
- Claude Desktop or Claude Code as your MCP client
- The MCP server built locally (cd mcp-server && npm install && npm run bundle)
Get a Gemini API key
Visit https://aistudio.google.com/apikey and create a new API key. This key is required for all image generation requests and must be set as the GEMINI_API_KEY environment variable.
Clone and build the MCP server
Clone the repository and build the bundled server. The MCP server lives in the mcp-server subdirectory and must be compiled before use.
git clone https://github.com/guinacio/claude-image-gen.git
cd claude-image-gen/mcp-server
npm install
npm run bundleConfigure Claude Code via CLI
Add the server to Claude Code using the mcp add command, pointing to the built bundle and supplying your Gemini API key.
claude mcp add --transport stdio media-pipeline \
--env GEMINI_API_KEY=your-api-key-here \
-- node /path/to/claude-image-gen/mcp-server/build/bundle.jsSet optional environment variables
You can customize the default model, output directory, and request timeout. IMAGE_OUTPUT_DIR controls where generated images are saved on disk.
export GEMINI_DEFAULT_MODEL=gemini-3-pro-image-preview
export IMAGE_OUTPUT_DIR=./generated-images
export GEMINI_REQUEST_TIMEOUT_MS=60000Verify the server is working
In Claude Code, ask it to generate a simple test image. The server will call the Gemini API and return the saved file path. Check that the file exists in your configured IMAGE_OUTPUT_DIR.
Claude Image Gen Examples
Client configuration
Add this to your ~/.claude.json mcpServers block to configure the media-pipeline server with all environment variables.
{
"mcpServers": {
"media-pipeline": {
"command": "node",
"args": ["/path/to/claude-image-gen/mcp-server/build/bundle.js"],
"env": {
"GEMINI_API_KEY": "your-gemini-api-key",
"GEMINI_DEFAULT_MODEL": "gemini-3-pro-image-preview",
"IMAGE_OUTPUT_DIR": "./generated-images",
"GEMINI_REQUEST_TIMEOUT_MS": "60000",
"MEDIA_PIPELINE_LOG_LEVEL": "info"
}
}
}
}Prompts to try
Example prompts for generating images via the create_asset tool in Claude Code or Claude Desktop.
- "Use create_asset to generate a hero image for a fintech startup website in 16:9 format"
- "Create a minimalist 3D illustration of abstract geometric shapes for a blog post header"
- "Generate a 1:1 square thumbnail image of a coffee cup with soft morning light for social media"
- "Create a mobile-friendly 9:16 vertical banner for a product launch announcement"Troubleshooting Claude Image Gen
GEMINI_API_KEY not found or authentication error
Ensure the GEMINI_API_KEY environment variable is set in the env block of your MCP config, not just in your shell. The server process does not inherit shell environment variables automatically.
Image generation times out
Increase GEMINI_REQUEST_TIMEOUT_MS (default 60000ms). Large or complex prompts with high-quality models can take longer. Try setting it to 120000 or switching to a faster model.
Module not found or build errors
Make sure you ran npm install and npm run bundle inside the mcp-server subdirectory specifically, not the repository root. The bundle.js path in your config must point to the built output in mcp-server/build/.
Frequently Asked Questions about Claude Image Gen
What is Claude Image Gen?
Claude Image Gen is a Model Context Protocol (MCP) server that ai-powered image generation using google gemini, integrated with claude code via skills or claude.ai via mcp (model context protocol). It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Claude Image Gen?
Follow the installation instructions on the Claude Image Gen GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Claude Image Gen?
Claude Image Gen works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Claude Image Gen free to use?
Yes, Claude Image Gen is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Claude Image Gen Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Claude Image Gen? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Claude Image Gen in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Claude Image Gen?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.