GPT-Image-1

You can use this MCP server to generate high-quality images with OpenAI’s GPT-Image-1 model. It exposes a simple, portable interface you can run locally or via an MCP client, automatically saves generated PNG images, and returns useful metadata about each generation. This guide gives you practical steps to install, configure, run, and troubleshoot the server so you can start generating images quickly.

How to use

Install and start the server through your MCP client, then call the image generation tools with your prompts. You can generate single images or multiple variations, specify target sizes, and receive local file paths for the saved images along with generation details.

How to install

Prerequisites: ensure you have Node.js 18 or higher installed on your machine and have an OpenAI API key with access to GPT-Image-1.

1. Get your OpenAI API Key. Create or log in to your OpenAI account and generate an API key in the API Keys section.

2. Install via universal npx configuration. This method works on any machine with Node.js and keeps you up to date automatically.

{
  "mcpServers": {
    "gpt-image-1": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/PierrunoYT/gpt-image-1-mcp-server.git"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here"
      }
    }
  }
}

Configuration and local installation

If you prefer running a local instance, use the path helper to get an absolute path to the server and run it directly.

Standard local installation example shown for a Claude or similar desktop integration uses a node command pointing to the built server.

{
  "mcpServers": {
    "gpt-image-1": {
      "command": "node",
      "args": ["path/to/gpt-image-1-mcp-server/build/index.js"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here"
      }
    }
  }
}

Additional configuration notes

The server supports multiple image sizes and batch generation, saves images automatically to a local images directory, and provides detailed responses with local file paths and metadata.

Troubleshooting and tips

• Ensure your OpenAI API key is valid and has access to GPT-Image-1. - If the server starts but cannot generate images, check that you can reach the OpenAI API and that your key is set in the environment. - Use the universal npx approach for maximum portability across different machines.

Tools and capabilities

Two generation tools are exposed for image creation with GPT-Image-1. They provide standard processing and an enhanced variation mode with style and quality controls.

Security and best practices

Keep your OpenAI API key secure. Do not expose it in public repositories or shared configurations. Use environment variables to pass keys to the MCP runtime and restrict access to your local machine or trusted networks.

Notes

The MCP server is designed to work without requiring a local installation beyond Node.js. It gracefully handles missing API keys and includes robust error reporting to help you diagnose issues quickly.

Available tools

gpt_image_1_generate

Generate images using GPT-Image-1 with standard processing. Parameters: prompt, size, n. Returns local file paths and metadata.

gpt_image_1_generate_with_variations

Generate images with enhanced style control and quality options. Parameters: prompt, size, n, style, quality. Returns local file paths and metadata.