@ramarivera/gpt-image-mcp

@ramarivera/gpt-image-mcp

A Model Context Protocol (MCP) server for generating and editing images using the OpenAI gpt-image-2 model.

🚀 Quick Start

Run this MCP server directly using NPX without installing it. View on npm.

npx -y @ramarivera/gpt-image-mcp

The -y flag automatically answers "yes" to any prompts that might appear during the installation process.

📋 Prerequisites

Node.js (v14 or higher)

OpenAI API key with access to gpt-image-2

🔑 Environment Variables

Variable	Required	Description
OPENAI_API_KEY	✅ Yes	Your OpenAI API key with access to GPT Image models, including gpt-image-2
GPT_IMAGE_OUTPUT_DIR	❌ No	Custom directory for saving generated images (defaults to user's Pictures folder under gpt-image-2 subfolder)

💻 Example Usage with NPX

Operating System	Command Line Example
Linux/macOS	# Set your OpenAI API key export OPENAI_API_KEY=sk-your-openai-api-key # Optional: Set custom output directory export GPT_IMAGE_OUTPUT_DIR=/home/username/Pictures/ai-generated-images # Run the server with NPX npx -y @ramarivera/gpt-image-mcp
Windows (PowerShell)	# Set your OpenAI API key $env:OPENAI_API_KEY = "sk-your-openai-api-key" # Optional: Set custom output directory $env:GPT_IMAGE_OUTPUT_DIR = "C:\Users\username\Pictures\ai-generated-images" # Run the server with NPX npx -y @ramarivera/gpt-image-mcp
Windows (Command Prompt)	:: Set your OpenAI API key set OPENAI_API_KEY=sk-your-openai-api-key :: Optional: Set custom output directory set GPT_IMAGE_OUTPUT_DIR=C:\Users\username\Pictures\ai-generated-images :: Run the server with NPX npx -y @ramarivera/gpt-image-mcp

🔌 Integration with MCP Clients

🛠️ Setting Up in an MCP Client

Step 1: Locate Settings File For Roo: c:\Users\<username>\AppData\Roaming\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\mcp_settings.json For VS Code MCP Extension: Check your extension documentation for the settings file location For Cursor: ~/.config/cursor/mcp_settings.json (Linux/macOS) or %APPDATA%\Cursor\mcp_settings.json (Windows) For Augment: ~/.config/augment/mcp_settings.json (Linux/macOS) or %APPDATA%\Augment\mcp_settings.json (Windows) For Windsurf: ~/.config/windsurf/mcp_settings.json (Linux/macOS) or %APPDATA%\Windsurf\mcp_settings.json (Windows)

Step 2: Add Configuration Add the following configuration to the mcpServers object:

{
  "mcpServers": {
    "gpt-image-2": {
      "command": "npx",
      "args": [
        "-y",
        "@ramarivera/gpt-image-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "PASTE YOUR OPEN-AI KEY HERE",
        "GPT_IMAGE_OUTPUT_DIR": "OPTIONAL: PATH TO SAVE GENERATED IMAGES"
      }
    }
  }
}

Example Configurations for Different Operating Systems

Operating System	Example Configuration
Windows	{ "mcpServers": { "gpt-image-2": { "command": "npx", "args": ["-y", "@ramarivera/gpt-image-mcp"], "env": { "OPENAI_API_KEY": "sk-your-openai-api-key", "GPT_IMAGE_OUTPUT_DIR": "C:\\Users\\username\\Pictures\\ai-generated-images" } } } }
Linux/macOS	{ "mcpServers": { "gpt-image-2": { "command": "npx", "args": ["-y", "@ramarivera/gpt-image-mcp"], "env": { "OPENAI_API_KEY": "sk-your-openai-api-key", "GPT_IMAGE_OUTPUT_DIR": "/home/username/Pictures/ai-generated-images" } } } }

Note: For Windows paths, use double backslashes (\\) to escape the backslash character in JSON. For Linux/macOS, use forward slashes (/).

✨ Features

🎨 Core Tools create_image: Generate new images from text prompts create_image_edit: Edit existing images with text prompts and masks

🚀 Key Benefits Simple integration with MCP clients Full access to OpenAI's gpt-image-2 capabilities Streamlined workflow for AI image generation

💡 Enhanced Capabilities

📊 Output & Formatting ✅ Beautifully Formatted Output: Responses include emojis and detailed information ✅ Automatic Image Saving: All generated images saved to disk for easy access ✅ Detailed Token Usage: View token consumption for each request

⚙️ Configuration & Handling ✅ Configurable Output Directory: Customize where images are saved ✅ File Path Support: Edit images using file paths instead of base64 encoding ✅ Comprehensive Error Handling: Detailed error reporting with specific error codes, descriptions, and troubleshooting suggestions

🔄 How It Works

🖼️ Image Generation	✏️ Image Editing
Server receives prompt and parameters Calls OpenAI API using the gpt-image-2 model by default API returns base64-encoded images Server saves images to configured directory Returns formatted response with paths and metadata	Server receives image, prompt, and optional mask For file paths, reads and prepares files for API Uses direct curl command for proper MIME handling API returns base64-encoded edited images Server saves images to configured directory Returns formatted response with paths and metadata

📁 Output Directory Behavior

📂 Storage Location 🔹 Default Location: User's Pictures folder under gpt-image-2 subfolder (e.g., C:\Users\username\Pictures\gpt-image-2 on Windows) 🔹 Custom Location: Set via GPT_IMAGE_OUTPUT_DIR environment variable 🔹 Fallback Location: ./generated-images (if Pictures folder can't be determined)

🗂️ File Management 🔹 Directory Creation: Automatically creates output directory if it doesn't exist 🔹 File Naming: Images saved with timestamped filenames (e.g., image-2023-05-05T12-34-56-789Z.png) 🔹 Cross-Platform: Works on Windows, macOS, and Linux with appropriate Pictures folder detection

Installation & Usage

NPM Package

This package is available on npm: @ramarivera/gpt-image-mcp

You can install it globally:

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

Or run it directly with npx as shown in the Quick Start section.

Tool: create_image

Generates a new image based on a text prompt.

Parameters

Parameter	Type	Required	Description
prompt	string	Yes	The text description of the image to generate (max 32,000 chars)
size	string	No	Image size: auto (default) or any GPT Image 2-compatible WIDTHxHEIGHT value: both edges multiples of 16, max edge 3840px, ratio at most 3:1, total pixels 655,360–8,294,400
quality	string	No	Image quality: auto (default), low, medium, or high
n	integer	No	Number of images to generate (1-10, default: 1)
background	string	No	Background style: auto (default) or opaque. GPT Image 2 does not support transparent backgrounds.
output_format	string	No	Output format: png (default), jpeg, or webp
output_compression	integer	No	Compression level (0-100) for JPEG/WebP output
user	string	No	User identifier for OpenAI usage tracking
moderation	string	No	Moderation level: "low" or "auto" (default)

Example

<use_mcp_tool>
<server_name>gpt-image-2</server_name>
<tool_name>create_image</tool_name>
<arguments>
{
  "prompt": "A futuristic city skyline at sunset, digital art",
  "size": "1024x1024",
  "quality": "high",
  "n": 1,
  "background": "auto"
}
</arguments>
</use_mcp_tool>

Response

The tool returns:

• A formatted text message with details about the generated image(s)
• The image(s) as base64-encoded data
• Metadata including token usage and file paths

Tool: create_image_edit

Edits an existing image based on a text prompt and optional mask.

Parameters

Parameter	Type	Required	Description
image	string, object, or array	Yes	The image(s) to edit (base64 string or file path object)
prompt	string	Yes	The text description of the desired edit (max 32,000 chars)
mask	string or object	No	The mask that defines areas to edit (base64 string or file path object)
size	string	No	Image size: auto (default) or any GPT Image 2-compatible WIDTHxHEIGHT value
quality	string	No	Image quality: auto (default), low, medium, or high
n	integer	No	Number of images to generate (1-10, default: 1)
background	string	No	Background style: auto (default) or opaque. GPT Image 2 does not support transparent backgrounds.
output_format	string	No	Output format: png (default), jpeg, or webp
output_compression	integer	No	Compression level (0-100) for JPEG/WebP output
user	string	No	User identifier for OpenAI usage tracking

Example with Base64 Encoded Image

<use_mcp_tool>
<server_name>gpt-image-2</server_name>
<tool_name>create_image_edit</tool_name>
<arguments>
{
  "image": "BASE64_ENCODED_IMAGE_STRING",
  "prompt": "Add a small robot in the corner",
  "mask": "BASE64_ENCODED_MASK_STRING",
  "quality": "high",
  "output_format": "png"
}
</arguments>
</use_mcp_tool>

Example with File Path

<use_mcp_tool>
<server_name>gpt-image-2</server_name>
<tool_name>create_image_edit</tool_name>
<arguments>
{
  "image": {
    "filePath": "C:/path/to/your/image.png"
  },
  "prompt": "Add a small robot in the corner",
  "mask": {
    "filePath": "C:/path/to/your/mask.png"
  },
  "quality": "high"
}
</arguments>
</use_mcp_tool>

Response

The tool returns:

• A formatted text message with details about the edited image(s)
• The edited image(s) as base64-encoded data
• Metadata including token usage and file paths

🔧 Troubleshooting

🚨 Common Issues

Issue	Solution
🖼️ MIME Type Errors Errors related to image format or MIME type handling	Ensure image files have the correct extension (.png, .jpg, etc.) that matches their actual format. The server uses file extensions to determine MIME types.
🔑 API Key Issues Authentication errors with OpenAI API	Verify your OpenAI API key is correct and has access to GPT Image models, including gpt-image-2. Check for any spaces or special characters that might have been accidentally included.
🛠️ Build Errors Issues when building from source	Ensure you have the correct TypeScript version installed (v5.3.3 or compatible) and that your tsconfig.json is properly configured. Run npm install to ensure all dependencies are installed.
📁 Output Directory Issues Problems with saving generated images	Check if the process has write permissions to the configured output directory. Try using an absolute path for GPT_IMAGE_OUTPUT_DIR if relative paths aren't working.

🔍 Error Handling and Reporting

The MCP server includes comprehensive error handling that provides detailed information when something goes wrong. When an error occurs:

• Error Format: All errors are returned with:

  • A clear error message describing what went wrong
  • The specific error code or type
  • Additional context about the error when available

• AI Assistant Behavior: When using this MCP server with AI assistants:

  • The AI will always report the full error message to help with troubleshooting
  • The AI will explain the likely cause of the error in plain language
  • The AI will suggest specific steps to resolve the issue

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

License Summary

The MIT License is a permissive license that is short and to the point. It lets people do anything with your code with proper attribution and without warranty.

You are free to:

• Use the software commercially
• Modify the software
• Distribute the software
• Use and modify the software privately

Under the following terms:

• Include the original copyright notice and the license notice in all copies or substantial uses of the work

Limitations:

• The authors provide no warranty with the software and are not liable for any damages

🙏 Acknowledgments

For providing GPT Image models, including gpt-image-2

For the protocol specification

Report Bug • Request Feature • Visit Our Website

Developed with ❤️ by CLOUDWERX