Name: ComfyUI MCP Server by zjf2671
Author: zjf2671

LABSCO SUMMARY

Your ComfyUI graphs, called by name from a chat.

The design keeps the hard part where it belongs: the workflow is authored and debugged in ComfyUI, and this only swaps prompt and size into it. That means the first job is exporting your graph in API format and confirming it runs in ComfyUI on its own — the sample workflows also need a plugin installed on the ComfyUI side, which the README links a walkthrough for.

What it is

A bridge between an assistant and a ComfyUI instance running on your machine. Workflow JSON files in a directory are loaded at startup and exposed as resources; a request picks one and substitutes the prompt and dimensions into it.

What you get

Text-to-image generation against whichever workflow you select
Image-to-image, background removal and Kontext image editing, using the sample workflows shipped with the project
Prompt and size are replaced inside the workflow at call time, so one workflow file serves many requests
Every JSON workflow in the workflows directory is registered as a resource when the server starts — drop a new file in and restart
Defaults are the t2image_bizyair_flux workflow at 1024x1024

Requirements

Python 3.12 or newer and a running ComfyUI instance — the default address is http://127.0.0.1:8188, set with COMFYUI_API_BASE. Install as uvx hh-mcp-comfyui, pip install hh_mcp_comfyui, or the container image zjf2671/hh-mcp-comfyui. COMFYUI_WORKFLOWS_DIR points at your workflow folder; your own workflows must be exported from ComfyUI in API JSON format.

Setup effort

One command — uvx hh-mcp-comfyui

See installation options

USE CASES

01

Generating an image without leaving the conversation

Pick a loaded workflow, give it a prompt, and the size defaults to 1024x1024 unless you say otherwise.

02

Editing an image you already have

The image-to-image, background-removal and Kontext workflows cover the common edits.

03

Using your own graph

Export from ComfyUI in API JSON format, drop it in the workflows directory, restart, and it registers as a resource.

BEFORE YOU INSTALL

What to know first

Requires

uvx on PATH

Where it runs

All 7 documented setups run the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

uvx hh-mcp-comfyui

MCP Clients

Cherry Studio — uvx, Cline — uvx, Cursor — uvx

JSON

{
  "mcpServers": {
    "hh-mcp-comfyui": {
      "command": "uvx",
      "args": [
        "hh-mcp-comfyui@latest"
      ],
      "env": {
        "COMFYUI_API_BASE": "http://127.0.0.1:8188",
        "COMFYUI_WORKFLOWS_DIR": "/path/hh-mcp-comfyui/workflows"
      }
    }
  }
}

Cherry Studio — pip, Cline — pip, Cursor — pip

JSON

{
  "mcpServers": {
    "hh-mcp-comfyui": {
      "command": "python",
      "args": [
        "-m",
        "hh_mcp_comfyui"
      ],
      "env": {
        "COMFYUI_API_BASE": "http://127.0.0.1:8188",
        "COMFYUI_WORKFLOWS_DIR": "/path/hh-mcp-comfyui/workflows"
      }
    }
  }
}

Docker

DOCKER · JSON

{
  "mcpServers": {
    "hh-mcp-comfyui": {
      "command": "docker",
      "args": [
        "run",
        "--net=host",
        "-v",
        "/path/hh-mcp-comfyui/workflows:/app/workflows",
        "-i",
        "--rm",
        "zjf2671/hh-mcp-comfyui:latest"
      ],
      "env": {
        "COMFYUI_API_BASE": "http://127.0.0.1:8188"
      }
    }
  }
}

ComfyUI MCP Server by zjf2671