comfyui-mcp-server
If you are the rightful owner of comfyui-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A lightweight Python-based MCP server interfacing with ComfyUI for image generation via AI agent requests.
The ComfyUI MCP Server is a Python-based server that uses the Model Context Protocol (MCP) to facilitate communication between AI agents and a local ComfyUI instance. It allows for programmatic image generation by sending requests over WebSocket. The server supports flexible workflow selection and dynamic parameters such as prompt, width, height, and model. The generated images are returned as URLs served by ComfyUI. The server requires Python 3.10+, ComfyUI running locally, and dependencies like requests, websockets, and mcp. Users can clone the repository, install dependencies, and start the server to begin sending image generation requests.
Features
- Flexible workflow selection for image generation.
- Dynamic parameter support including prompt, width, height, and model.
- WebSocket-based communication for real-time requests.
- Returns image URLs served by ComfyUI.
- Customizable client for testing and sending requests.
