Enables image generation and editing through OpenAI's GPT-4o/gpt-image-1 APIs using the Model Context Protocol.
Sponsored
This tool provides a Model Context Protocol (MCP) server, allowing seamless integration with OpenAI's image generation and editing capabilities. Leveraging GPT-4o/gpt-image-1, it offers functionalities like generating images from text prompts and editing existing images with advanced prompt control. It supports various MCP-compatible clients, including Claude Desktop, Cursor, VSCode, and Windsurf, streamlining image-based workflows within these environments.
Key Features
01Edits or extends images using a prompt and optional mask, supporting both file paths and base64 input.
02Saves generated images directly to disk or receives them as base64.
037 GitHub stars
04Generates images from text prompts with advanced options (size, quality, background, etc.).
05Supports creating up to 10 images at once.
06Allows precise edits with mask images to control where edits are applied.
Use Cases
01Generating custom images from text descriptions for various applications.
02Editing and enhancing existing images using natural language prompts.
03Integrating image generation and editing into MCP-compatible development environments.
