Integrates OpenAI's powerful image generation and editing APIs for use within Model Context Protocol environments.
Sponsored
This tool serves as a Model Context Protocol (MCP) server, bringing OpenAI's advanced GPT-4o/gpt-image-1 image generation and editing capabilities to various MCP-compatible clients. It allows users to effortlessly create new images from text prompts and perform sophisticated edits like inpainting, outpainting, and compositing with precise control. Designed for seamless integration, it supports popular platforms such as Claude Desktop, Cursor, VSCode, and Windsurf, simplifying AI-driven image manipulation within your preferred workflow.
Key Features
01Supports common aspect ratios (e.g., 16:9, 1:1, 9:16) which automatically map to OpenAI's supported sizes.
02Ability to generate multiple images (up to 10) in a single request.
030 GitHub stars
04Generate images from text prompts using OpenAI's latest models.
05Edit or extend images using prompts and optional masks for inpainting, outpainting, and compositing.
06Save generated images directly to disk or receive them as base64 strings.
Use Cases
01Creating and modifying AI-generated images directly within MCP-compatible clients like Claude Desktop, VSCode, or Cursor.
02Automating image content creation and modification for design, development, or content production workflows.
03Performing advanced image manipulation tasks such as removing elements (inpainting) or extending images (outpainting) with AI.
