gpt-image-1

A Model Context Protocol (MCP) server that uses OpenAI’s gpt-image-1 model for generating and editing images.

Features

• 🖼️ Generate new images from text prompts
• ✏️ Edit existing images with text prompts and masks
• 🎨 Support for various image sizes and quality settings
• 💾 Automatic saving of generated images to disk
• 🔧 Configurable output directory for easy management
• 🔒 Secure API key handling through environment variables
• 📊 Detailed token usage reporting for each request

Use Cases

• Rapid prototyping of UI/UX designs by generating concept images from text descriptions
• Creating custom illustrations for blog posts or marketing materials without relying on stock images
• Editing product photos to quickly visualize different color schemes or minor design changes
• Generating multiple variations of an image concept for A/B testing in digital marketing campaigns

How to Use It

Prerequisites:

• Node.js v14 or higher
• OpenAI API key with access to gpt-image-1 model

Installation:

npm install -g @cloudwerxlab/gpt-image-1-mcp

Set up environment variables:

export OPENAI_API_KEY=your-api-key-here
export GPT_IMAGE_OUTPUT_DIR=/path/to/save/images

Run the server:

npx @cloudwerxlab/gpt-image-1-mcp

Add the following configuration to your MCP client’s settings file:

{
 "mcpServers": {
   "gpt-image-1": {
     "command": "npx",
     "args": ["-y", "@cloudwerxlab/gpt-image-1-mcp"],
     "env": {
       "OPENAI_API_KEY": "your-api-key-here",
       "GPT_IMAGE_OUTPUT_DIR": "/path/to/save/images"
     }
   }
 }
}

Use the create_image tool to generate images:

{
 "prompt": "A futuristic city skyline at sunset, digital art",
 "size": "1024x1024",
 "quality": "high",
 "n": 1
}

Use the create_image_edit tool to edit images:

{
 "image": {"filePath": "/path/to/image.png"},
 "prompt": "Add a small robot in the corner",
 "mask": {"filePath": "/path/to/mask.png"},
 "quality": "high"
}

FAQs

Q: Can I use this server with any MCP client?
A: Yes, this server is designed to work with any MCP-compatible client, including popular ones like Roo, VS Code MCP Extension, Cursor, Augment, and Windsurf.

Q: How do I handle errors related to image format or MIME types?
A: Ensure that your image files have the correct file extension (.png, .jpg, etc.) matching their actual format. The server uses file extensions to determine MIME types.

Q: What should I do if I encounter API key issues?
A: Verify that your OpenAI API key is correct and has access to the gpt-image-1 model. Double-check for any accidental spaces or special characters in the key.

Q: How can I customize where the generated images are saved?
A: Set the GPT_IMAGE_OUTPUT_DIR environment variable to your desired output directory. If not set, images will be saved in a gpt-image-1 subfolder within your system’s Pictures folder.

Q: Is there a limit to the number of images I can generate?
A: You can generate up to 10 images per request using the n parameter. However, be mindful of your OpenAI API usage limits and costs.