How do I use gpt-image-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gpt-image-mcp Generate a landscape image of a mountain at sunset." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

gpt-image-mcp

by naporin0624

Overview Schema Related Servers Score Discussions

TypeScript

gpt-image MCP

npm version License: MIT OpenAI Documentation

MCP server for AI-powered image generation using OpenAI's gpt-image-1 and gpt-image-2 models with advanced text rendering and native transparency support.

Features

Advanced text rendering with gpt-image-1 - Crisp, legible typography and logos in generated images
Native transparency support - Built-in transparent background without post-processing
Multi-format output (PNG, JPEG, WebP) - Flexible format options with optimized compression
Flexible dimensions and aspect ratios - Square (1024×1024), landscape (1536×1024), and portrait (1024×1536)
Batch image editing capabilities - Process multiple images with parallel processing
Token-optimized MCP responses - Efficient response formats for MCP protocol limits

Installation

Recommended: Using npx

{
  "mcpServers": {
    "gpt-image-mcp": {
      "command": "npx",
      "args": ["@napolab/gpt-image-mcp"],
      "env": {
        "OPENAI_API_KEY": "sk-your-api-key"
      }
    }
  }
}

Alternative: Local Installation

npm install -g @napolab/gpt-image-mcp

Claude Desktop Configuration

Configure in ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "gpt-image-mcp": {
      "command": "npx",
      "args": ["@napolab/gpt-image-mcp"],
      "env": {
        "OPENAI_API_KEY": "sk-your-api-key"
      }
    }
  }
}

Configuration

Environment Variables

Variable	Required	Default	Description
`OPENAI_API_KEY`	Yes	-	Your OpenAI API key
`DEFAULT_OUTPUT_DIR`	No	`./generated_images`	Default output directory
`DEFAULT_IMAGE_SIZE`	No	`1024x1024`	Default image dimensions
`DEFAULT_IMAGE_QUALITY`	No	`standard`	Default quality (standard/hd)
`DEFAULT_OUTPUT_FORMAT`	No	`png`	Default format (png/jpeg/webp)

Available Tools

generate-image

Generate images using gpt-image-1 with advanced text rendering and superior instruction following.

Parameters:

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Image description (English only)
`aspect_ratio`	string	No	`square`	"square", "landscape", or "portrait"
`quality`	string	No	`standard`	"standard" or "hd"
`output_directory`	string	No	`./generated_images`	Directory to save the image
`filename`	string	No	-	Custom filename
`save_to_file`	boolean	No	`true`	Whether to save locally
`include_base64`	boolean	No	`false`	Include base64 in response

Example:

await client.callTool("generate-image", {
  prompt: "A serene Japanese garden with cherry blossoms",
  aspect_ratio: "landscape",
  quality: "hd",
});

edit-image

Edit existing images with AI-powered modifications including inpainting, outpainting, style transfer, and background changes.

Parameters:

Parameter	Type	Required	Default	Description
`source_image`	object	Yes	-	Image input (URL, base64, or local file)
`edit_prompt`	string	Yes	-	Description of desired changes (English only)
`edit_type`	string	Yes	-	Type of edit to perform
`strength`	number	No	`0.8`	Edit strength (0.0 to 1.0)
`preserve_composition`	boolean	No	`true`	Maintain original composition
`output_format`	string	No	`png`	Output format

Edit Types:

inpaint - Fill in or modify specific areas
outpaint - Extend image beyond boundaries
background_change - Replace or modify background
style_transfer - Apply artistic styles
object_removal - Remove unwanted objects
variation - Create variations of original

Example:

await client.callTool("edit-image", {
  source_image: {
    type: "local",
    value: "/path/to/image.jpg",
  },
  edit_prompt: "Add a sunset sky background",
  edit_type: "background_change",
});

batch-edit

Apply the same edit to multiple images efficiently with parallel processing.

Parameters:

Parameter	Type	Required	Default	Description
`images`	array	Yes	-	Array of image inputs
`edit_prompt`	string	Yes	-	Edit description (English only)
`edit_type`	string	Yes	-	Type of edit to apply
`batch_settings`	object	No	-	Batch processing configuration

Example:

await client.callTool("batch-edit", {
  images: [
    { type: "local", value: "/path/to/image1.jpg" },
    { type: "local", value: "/path/to/image2.jpg" },
  ],
  edit_prompt: "Apply vintage sepia filter",
  edit_type: "style_transfer",
});

Usage Examples

Basic Image Generation

// Generate a simple image
const result = await client.callTool("generate-image", {
  prompt: "A modern minimalist logo design",
  aspect_ratio: "square",
  quality: "hd",
});

console.log("Generated image:", result.data.file_path);

Advanced Options

// Generate with all parameters
const result = await client.callTool("generate-image", {
  prompt: "Professional product photography of a smartphone",
  aspect_ratio: "portrait",
  quality: "hd",
  output_directory: "./product_images",
  filename: "smartphone_hero",
  output_format: "png",
  include_base64: true,
});

Image Editing

// Generate base image
const baseImage = await client.callTool("generate-image", {
  prompt: "A mountain landscape",
  aspect_ratio: "landscape",
});

// Edit the generated image
const editedImage = await client.callTool("edit-image", {
  source_image: {
    type: "local",
    value: baseImage.data.file_path,
  },
  edit_prompt: "Add dramatic storm clouds",
  edit_type: "background_change",
  strength: 0.7,
});

Batch Processing

// Process multiple images
const result = await client.callTool("batch-edit", {
  images: [
    { type: "local", value: "image1.jpg" },
    { type: "local", value: "image2.jpg" },
    { type: "local", value: "image3.jpg" },
  ],
  edit_prompt: "Apply Instagram-style filter",
  edit_type: "style_transfer",
  batch_settings: {
    max_concurrent: 3,
    error_handling: "continue_on_error",
  },
});

Development

Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Submit a pull request

Testing

# Run tests
npm test

# Run tests in watch mode
npm run test:watch

# Run linting
npm run lint

# Type checking
npm run typecheck

Building

# Build for production
npm run build

# Development mode with hot reload
npm run dev

License

MIT License - see the LICENSE file for details.

Support

Documentation - Full documentation and examples
GitHub Issues
OpenAI API Documentation
MCP Protocol Documentation

This server cannot be installed

license - not tested

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

0dRelease cycle

4Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly
Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
OpenAI
open source

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/naporin0624/gpt-image-1-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server