comfyui-mcp
comfyui-mcp is an MCP server and sidebar agent that lets an AI assistant generate images, video, and audio in ComfyUI for creators and developers.
What it is good for
- Generating images, video, and audio in ComfyUI from plain-language requests
- Editing a live ComfyUI node graph by describing changes in plain language
- Running a local image generation setup without sending prompts to a cloud service
- Connecting ComfyUI to Claude, ChatGPT, Gemini, or a local Ollama model
At a glance
- Who it is for
- Setup difficulty
- Technical ยท Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- MCP server or connector
- Tasks
- Works with
- ComfyUI, Claude Code, Claude, ChatGPT, Gemini, Ollama
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 929
GitHub numbers as of Nov 16, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is comfyui-mcp free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use comfyui-mcp?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does comfyui-mcp work with?
- According to its own documentation, it works with ComfyUI, Claude Code, Claude, ChatGPT, Gemini, and Ollama.
- What is comfyui-mcp good for?
- Generating images, video, and audio in ComfyUI from plain-language requests, editing a live ComfyUI node graph by describing changes in plain language, running a local image generation setup without sending prompts to a cloud service, and connecting ComfyUI to Claude, ChatGPT, Gemini, or a local Ollama model.
Similar agents to comfyui-mcp
- comfy-mcp
comfy-mcp is an MCP server that lets AI apps like Claude run and manage a ComfyUI image setup on your own computer.
- ComfyUI
ComfyUI is a node-based app that builds and runs image, video, and audio generation workflows for visual creators.
- gflow-cli
gflow-cli is a command-line tool and MCP server that generates Veo videos and Imagen images in Google Flow for batch and scripted work.
- OmniGet
OmniGet is a local MCP server that gives your coding agent downloads, media conversion, files and system cleanup on your desktop.
- flow-mcp
flow-mcp is an MCP server that lets Claude or Codex drive Google Flow to make AI videos using your Google AI credits, for anyone who wants to create video from chat.
- OpenChatCut
OpenChatCut is an open-source desktop video editor that lets an AI agent edit a real multitrack timeline for creators and developers.