image-generator MCP Server

Use This MCP server To

Generate images from text prompts for creative projects Save generated images locally for easy access Integrate image generation into AI-powered workflows Prototype visual concepts quickly with AI assistance Automate image creation in content production pipelines

README

image-generator MCP Server

An mcp server that generates images based on image prompts

This is a TypeScript-based MCP server that implements image generation using OPENAI's dall-e-3 image generation model.

Features

Tools

generate_image - Generate an image for given prompt
- Takes prompt as a required parameter
- Takes imageName as a required parameter to save the generated image in a generated-images directory on your desktop

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "command": "image-generator",
      "env": {
        "OPENAI_API_KEY": "<your-openai-api-key>"
    }
  }
}

Make sure to replace <your-openai-api-key> with your actual OPENAI Api Key.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

image-generator-mcp-server FAQ

How do I install the image-generator-mcp-server?

Install dependencies with 'npm install', build with 'npm run build', and optionally run 'npm run watch' for development.

How do I configure the server for use with Claude Desktop?

Add the server config to Claude Desktop's config file with the command 'image-generator' and set your OpenAI API key in the environment variables.

Where are generated images saved?

Images are saved in a 'generated-images' directory on your desktop, named according to the 'imageName' parameter.

What parameters does the 'generate_image' tool require?

It requires a 'prompt' for the image description and an 'imageName' to save the file.

Can I use this server with LLM providers other than OpenAI?

While this server uses OpenAI's DALL·E-3 model, MCP supports integration with other providers like Anthropic's Claude and Google Gemini for different capabilities.

Is this server suitable for development and production?

Yes, it supports development with auto-rebuild via 'npm run watch' and can be built for production use.

What programming language is the server written in?

The server is implemented in TypeScript, facilitating easy customization and extension.