comfy-agent-mcp

Local MCP server and CLI that drive ComfyUI with Qwen Image 2.1 so Cursor (or any MCP client) can generate and edit images on your machine.

Features

• generate_image — text-to-image with aspect ratio, megapixels, or exact width/height (64–2048)

• edit_image — edit an existing PNG/JPEG with an instruction (e.g. “remove Chinese text, keep the rest”)

• Seed reuse as a decimal string for reproducible runs

• Same capabilities available from the Python CLI (comfy_cli.py)

Related MCP server: comfyui-mcp

Requirements

• Node.js 18+

• Python 3.10+ with requests (py -m pip install requests)

• ComfyUI running locally at http://127.0.0.1:8188

• Qwen Image 2.1 models loaded in ComfyUI (matching workflow.json)

Setup

npm install
py -m pip install requests

Start ComfyUI, then run the MCP server:

npm start

Cursor MCP config

Point Cursor at server.mjs (adjust the path to your clone):

{
  "mcpServers": {
    "comfyui-local": {
      "command": "node",
      "args": ["E:/path/to/comfy-agent/server.mjs"]
    }
  }
}

On Windows the CLI is invoked with py. Ensure the Python launcher is on your PATH.

MCP tools

generate_image

Size tips: icons ~256–512, UI ~1024, cinematic up to 2048.

edit_image

Editing uses the source as a Qwen reference. Reusing a generation seed alone does not edit a picture — use edit_image.

CLI

# Generate
py comfy_cli.py --prompt "cyberpunk city at night" --aspect-ratio "16:9 (Widescreen)" --megapixels 1

# Exact size
py comfy_cli.py --prompt "app icon, flat" --width 256 --height 256

# Edit
py comfy_cli.py --image ./output/photo.png --prompt "Remove all overlaid text" --negative "text, letters"

# Machine-readable output
py comfy_cli.py --prompt "..." --json

Images are written to output/ by default (gitignored).

Project layout

License

MIT — see LICENSE.