openai-gpt-image-mcp

Name: openai-gpt-image-mcp
Author: SureScaleAI

@SureScaleAI

Repository

About openai-gpt-image-mcp

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

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is openai-gpt-image-mcp?

openai-gpt-image-mcp is a Model Context Protocol (MCP) server that provides image generation and editing capabilities via OpenAI's GPT-4o and gpt-image-1 APIs. It is designed for developers and users of MCP-compatible clients such as Claude Desktop, Cursor, VSCode, and Windsurf.

How to use openai-gpt-image-mcp?

Clone the repository, install dependencies with yarn install, and build with yarn build. Then add a configuration entry to your MCP client (e.g., Claude Desktop or VSCode) specifying the path to dist/index.js and your OpenAI API key (or Azure credentials). The server exposes two tools: create-image (generate images) and edit-image (edit images with optional mask). Image output can be saved to disk or returned as base64.

Key features of openai-gpt-image-mcp

Generate images from text prompts with size, quality, and background options.
Edit images using inpainting, outpainting, or compositing with a mask.
Supports file paths and base64 input for source images and masks.
Automatic file output when total image size exceeds the 1MB MCP payload limit.
Works with OpenAI and Azure OpenAI deployments.
Configurable working directory via the MCP_HF_WORK_DIR environment variable.

Use cases of openai-gpt-image-mcp

Generate up to 10 images at once from a single prompt for creative projects.
Edit specific regions of an image by providing a mask and a new description.
Integrate AI image generation directly into AI‑assisted code editors or chat clients.
Produce images as files for use in documents, presentations, or web content.

FAQ from openai-gpt-image-mcp

What dependencies are required to run openai-gpt-image-mcp?

You need Node.js, yarn (or npm), and an Internet connection. The server uses the OpenAI Node.js SDK and the MCP SDK.

How do I configure openai-gpt-image-mcp for Azure OpenAI?

Set the environment variables AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, and OPENAI_API_VERSION in the MCP client configuration instead of OPENAI_API_KEY.

What happens if the generated image is larger than 1MB?

The tool automatically saves the image to disk and returns the file path instead of base64. This avoids the 1MB payload limit of MCP clients like Claude Desktop.

Where are files saved by default?

If no file_output path is specified, images are saved to /tmp (or the directory set by the MCP_HF_WORK_DIR environment variable) with a unique filename.

What file path format is required for input images?

Absolute paths are required. On Unix/macOS/Linux use a leading / (e.g., /path/to/image.png), and on Windows include the drive letter followed by : (e.g., C:/path/to/image.png).

Comments

More AI & Agents MCP servers

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K