openai-gpt-image-mcp

openai-gpt-image-mcp

MCP-compatible server for image generation and editing via OpenAI APIs.

70
Stars
21
Forks
70
Watchers
0
Issues
Provides a Model Context Protocol (MCP) tool server that interfaces with OpenAI's GPT-4o/gpt-image-1 APIs to generate and edit images from text prompts. Supports advanced image editing operations including inpainting, outpainting, and compositing with customizable options. Integrates with MCP-compatible clients such as Claude Desktop, VSCode, Cursor, and Windsurf. Offers both base64 and file output for generated images, with automatic file handling for large images.

Key Features

Text-to-image generation using OpenAI's GPT models
Image editing including inpainting, outpainting, and compositing
Support for multiple input and output formats (file path, base64)
Configurable server for integration with MCP-compatible clients
Advanced prompt and parameter control (size, quality, background, etc.)
Automatic output switching for large files (base64 to file path)
Customizable environment and Azure deployment support
Batch image generation (generate up to 10 images at once)
Mask support in edit operations
Environment variable and env-file configuration

Use Cases

Generating custom images from textual prompts for creative projects
Editing images to add, remove, or modify content via prompts
Integrating AI-driven image operations into developer workflows within editors like VSCode or Cursor
Automating batch creation of marketing or social media images
Building tools for visual storytelling or design prototyping
Enhancing documentation or presentations with AI-generated visuals
Providing image generation capabilities in chatbots or digital assistants
Researching advanced AI-powered image manipulation techniques
Automating image content augmentation in enterprise applications
Supporting designers and artists with AI-assisted creativity tools

README

openai-gpt-image-mcp


A Model Context Protocol (MCP) tool server for OpenAI's GPT-4o/gpt-image-1 image generation and editing APIs.

  • Generate images from text prompts using OpenAI's latest models.
  • Edit images (inpainting, outpainting, compositing) with advanced prompt control.
  • Supports: Claude Desktop, Cursor, VSCode, Windsurf, and any MCP-compatible client.

✨ Features

  • create-image: Generate images from a prompt, with advanced options (size, quality, background, etc).
  • edit-image: Edit or extend images using a prompt and optional mask, supporting both file paths and base64 input.
  • File output: Save generated images directly to disk, or receive as base64.

🚀 Installation

sh
git clone https://github.com/SureScaleAI/openai-gpt-image-mcp.git
cd openai-gpt-image-mcp
yarn install
yarn build

🔑 Configuration

Add to Claude Desktop or VSCode (including Cursor/Windsurf) config:

json
{
  "mcpServers": {
    "openai-gpt-image-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js"],
      "env": { "OPENAI_API_KEY": "sk-..." }
    }
  }
}

Also supports Azure deployments:

json
{
  "mcpServers": {
    "openai-gpt-image-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js"],
      "env": { 
        "AZURE_OPENAI_API_KEY": "sk-...",
        "AZURE_OPENAI_ENDPOINT": "my.endpoint.com",
        "OPENAI_API_VERSION": "2024-12-01-preview"
      }
    }
  }
}

Also supports supplying an environment files:

json
{
  "mcpServers": {
    "openai-gpt-image-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js", "--env-file", "./deployment/.env"]
    }
  }
}

⚡ Advanced

  • For create-image, set n to generate up to 10 images at once.
  • For edit-image, provide a mask image (file path or base64) to control where edits are applied.
  • Provide an environment file with --env-file path/to/file/.env
  • See src/index.ts for all options.

🧑‍💻 Development

  • TypeScript source: src/index.ts
  • Build: yarn build
  • Run: node dist/index.js

📝 License

MIT


🩺 Troubleshooting

  • Make sure your OPENAI_API_KEY is valid and has image API access.
  • You must have a verified OpenAI organization. After verifying, it can take 15–20 minutes for image API access to activate.
  • File paths must be absolute.
    • Unix/macOS/Linux: Starting with / (e.g., /path/to/image.png)
    • Windows: Drive letter followed by : (e.g., C:/path/to/image.png or C:\path\to\image.png)
  • For file output, ensure the directory is writable.
  • If you see errors about file types, check your image file extensions and formats.

⚠️ Limitations & Large File Handling

  • 1MB Payload Limit: MCP clients (including Claude Desktop) have a hard 1MB limit for tool responses. Large images (especially high-res or multiple images) can easily exceed this limit if returned as base64.
  • Auto-Switch to File Output: If the total image size exceeds 1MB, the tool will automatically save images to disk and return the file path(s) instead of base64. This ensures compatibility and prevents errors like result exceeds maximum length of 1048576.
  • Default File Location: If you do not specify a file_output path, images will be saved to /tmp (or the directory set by the MCP_HF_WORK_DIR environment variable) with a unique filename.
  • Environment Variable:
    • MCP_HF_WORK_DIR: Set this to control where large images and file outputs are saved. Example: export MCP_HF_WORK_DIR=/your/desired/dir
  • Best Practice: For large or production images, always use file output and ensure your client is configured to handle file paths.

📚 References


🙏 Credits

Star History

Star History Chart

Repository Owner

SureScaleAI
SureScaleAI

Organization

Repository Details

Language TypeScript
Default Branch master
Size 8,884 KB
Contributors 2
License MIT License
MCP Verified Sep 1, 2025

Programming Languages

TypeScript
100%

Tags

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • Outsource MCP

    Outsource MCP

    Unified MCP server for multi-provider AI text and image generation

    Outsource MCP is a Model Context Protocol server that bridges AI applications with multiple model providers via a single unified interface. It enables AI tools and clients to access over 20 major providers for both text and image generation, streamlining model selection and API integration. Built on FastMCP and Agno agent frameworks, it supports flexible configuration and is compatible with MCP-enabled AI tools. Authentication is provider-specific, and all interactions use a simple standardized API format.

    • 26
    • MCP
    • gwbischof/outsource-mcp
  • OpenAPI-MCP

    OpenAPI-MCP

    Dockerized MCP server that transforms OpenAPI/Swagger specs into MCP-compatible tools.

    OpenAPI-MCP is a dockerized server that reads Swagger/OpenAPI specification files and generates corresponding Model Context Protocol (MCP) toolsets. It enables MCP-compatible clients to interact dynamically with APIs described by OpenAPI specs, automatically generating the necessary tool schemas and facilitating secure API key handling. The solution supports both local and remote API specs, offers filtering by tags and operations, and can be easily deployed using Docker.

    • 150
    • MCP
    • ckanthony/openapi-mcp
  • @nanana-ai/mcp-server-nano-banana

    @nanana-ai/mcp-server-nano-banana

    MCP server for Nanana AI image generation using Gemini's nano banana model.

    @nanana-ai/mcp-server-nano-banana serves as an MCP (Model Context Protocol) compatible server for facilitating image generation and transformation powered by the Gemini nano banana model. It enables clients like Claude Desktop to interact with Nanana AI, processing text prompts to generate images or transform existing images. The server can be easily configured with API tokens and integrated into desktop applications. Users can manage credentials, customize endpoints, and monitor credit usage seamlessly.

    • 3
    • MCP
    • nanana-app/mcp-server-nano-banana
  • piapi-mcp-server

    piapi-mcp-server

    TypeScript-based MCP server for PiAPI media content generation

    piapi-mcp-server is a TypeScript implementation of a Model Context Protocol (MCP) server that connects with PiAPI to enable media generation workflows from MCP-compatible applications. It handles image, video, music, TTS, 3D, and voice generation tasks using a wide range of supported models like Midjourney, Flux, Kling, LumaLabs, Udio, and more. Designed for easy integration with clients such as Claude Desktop, it includes an interactive MCP Inspector for development, testing, and debugging.

    • 62
    • MCP
    • apinetwork/piapi-mcp-server
  • Replicate Flux MCP

    Replicate Flux MCP

    MCP-compatible server for high-quality image and SVG generation via Replicate models.

    Replicate Flux MCP is an advanced Model Context Protocol (MCP) server designed to enable AI assistants to generate high-quality raster images and vector graphics. It leverages Replicate's Flux Schnell model for image synthesis and Recraft V3 SVG model for vector output, supporting seamless integration with AI platforms like Cursor, Claude Desktop, Smithery, and Glama.ai. Users can generate images and SVGs by simply providing natural language prompts, with support for parameter customization, batch processing, and variant creation.

    • 66
    • MCP
    • awkoy/replicate-flux-mcp
  • Amazon Bedrock MCP Server

    Amazon Bedrock MCP Server

    Model Control Protocol server for AI image generation via Amazon Bedrock's Nova Canvas.

    Amazon Bedrock MCP Server implements the Model Control Protocol to enable advanced AI image generation using Amazon's Nova Canvas model. It provides features like deterministic output through seed control, negative prompts, and configurable quality and image dimensions. Secure and flexible AWS credential management is supported, along with integration for Claude Desktop and robust input validation. The solution ensures high-quality, reproducible image generation workflows tailored for both developers and integrated applications.

    • 22
    • MCP
    • zxkane/mcp-server-amazon-bedrock
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results