ComfyUI MCP Server

Generate images from Claude using your local ComfyUI setup

README.md

Generate images from Claude using your local ComfyUI setup

Installation • Setup • What You Can Do • Configuration • Development


What is this?

ComfyUI MCP Server connects Claude Desktop (or Claude Code) to your local ComfyUI instance. Once set up, you can ask Claude to generate images and it will run them through Stable Diffusion, SDXL, or whatever checkpoint models you have installed -- no copy-pasting prompts between apps.

It works over MCP (Model Context Protocol), which means Claude treats your ComfyUI setup as a native tool.

Example conversation:

You:   Generate a watercolor painting of a coastal village at sunrise
Claude: I'll generate that using your SDXL model.
        [calls generate_image -> ComfyUI runs the workflow -> returns result]
        Done -- saved as ComfyUI-MCP_00042.png (14.2s)

How it works

Claude Desktop / Claude Code
        |
        v
  MCP Server (stdio)
        |
        v
  ComfyUI REST API (localhost:8188)
        |
        v
  Your GPU -> Stable Diffusion / SDXL / etc.

The server translates Claude's tool calls into ComfyUI workflow submissions, polls for completion, and returns the results.

Prerequisites

  • Python 3.11+
  • ComfyUI running locally (default: http://127.0.0.1:8188)
  • At least one checkpoint model installed in ComfyUI

Installation

git clone https://github.com/MatthewSnow2/comfyui-mcp.git
cd comfyui-mcp

python -m venv .venv
source .venv/bin/activate   # Linux/macOS
# .venv\Scripts\activate    # Windows

pip install -e ".[dev]"

Setup

1. Configure environment

Copy .env.example to .env and adjust if needed:

cp .env.example .env
Variable Default What it does
COMFYUI_URL http://127.0.0.1:8188 Where your ComfyUI is running
COMFYUI_OUTPUT_DIR ~/comfyui-output Where generated images get saved
COMFYUI_DEFAULT_MODEL sd_xl_base_1.0.safetensors Which checkpoint to use by default
COMFYUI_DEFAULT_STEPS 20 Sampling steps
COMFYUI_DEFAULT_WIDTH 1024 Image width (px)
COMFYUI_DEFAULT_HEIGHT 1024 Image height (px)
COMFYUI_DEFAULT_CFG_SCALE 7.0 CFG scale

2. Add to Claude Desktop

Add this block to your claude_desktop_config.json:

{
  "mcpServers": {
    "comfyui": {
      "command": "/path/to/comfyui-mcp/.venv/bin/comfyui-mcp",
      "env": {
        "COMFYUI_URL": "http://127.0.0.1:8188",
        "COMFYUI_DEFAULT_MODEL": "sd_xl_base_1.0.safetensors"
      }
    }
  }
}

Replace /path/to/comfyui-mcp with your actual install path.

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

3. Restart Claude Desktop

Restart the app. You should see "comfyui" listed in the MCP tools dropdown.

What you can do

Generate images

Ask Claude to generate an image from any text prompt. It handles prompt engineering, model selection, and parameter tuning.

Parameter Type Default Description
prompt string (required) What you want to see
negative_prompt string "" What to avoid
model string config default Checkpoint model name
width int 1024 Width in pixels
height int 1024 Height in pixels
steps int 20 Sampling steps (more = slower but often better)
cfg_scale float 7.0 How closely to follow the prompt
seed int -1 Random seed (-1 = random each time)

List your models

Ask "what models do I have?" and Claude will show every checkpoint installed in your ComfyUI.

Check queue status

Ask "what's in the queue?" to see how many jobs are pending, running, or completed.

Look up past generations

Give Claude a prompt ID from a previous generation and it will pull up the details.

Real usage examples

You:   What models do I have?
Claude: You have 3 checkpoints:
        - sd_xl_base_1.0.safetensors
        - dreamshaper_8.safetensors
        - realisticVision_v51.safetensors

You:   Generate a cyberpunk street scene using dreamshaper at 512x768
Claude: [runs generation with dreamshaper_8, 512x768]
        Done -- ComfyUI-MCP_00043.png (8.3s)

You:   Same scene but make it daytime and use realisticVision
Claude: [runs generation with realisticVision_v51, same dimensions]
        Done -- ComfyUI-MCP_00044.png (9.1s)

Development

Run tests

pytest

Lint an

Tools 4

generate_imageGenerates an image from a text prompt using ComfyUI workflows.
list_modelsLists all checkpoint models installed in the local ComfyUI instance.
check_queueChecks the current status of the ComfyUI job queue.
get_generation_detailsRetrieves details for a past image generation using its prompt ID.

Environment Variables

COMFYUI_URLThe URL where ComfyUI is running locally.
COMFYUI_OUTPUT_DIRDirectory where generated images are saved.
COMFYUI_DEFAULT_MODELDefault checkpoint model to use.
COMFYUI_DEFAULT_STEPSDefault number of sampling steps.
COMFYUI_DEFAULT_WIDTHDefault image width in pixels.
COMFYUI_DEFAULT_HEIGHTDefault image height in pixels.
COMFYUI_DEFAULT_CFG_SCALEDefault CFG scale value.

Try it

Generate a watercolor painting of a coastal village at sunrise
What models do I have installed in ComfyUI?
What is the current status of the ComfyUI queue?
Generate a cyberpunk street scene using dreamshaper at 512x768
Show me the details for the last image I generated

Frequently Asked Questions

What are the key features of ComfyUI MCP Server?

Direct integration between Claude and local ComfyUI instances. Automated image generation via natural language prompts. Capability to list and select specific checkpoint models. Real-time monitoring of ComfyUI queue status. Retrieval of historical generation details.

What can I use ComfyUI MCP Server for?

Rapid prototyping of AI-generated assets without leaving the Claude interface. Managing complex image generation workflows using natural language instructions. Monitoring long-running batch image generation tasks directly from the chat. Switching between different artistic styles by querying and selecting installed checkpoints.

How do I install ComfyUI MCP Server?

Install ComfyUI MCP Server by running: git clone https://github.com/MatthewSnow2/comfyui-mcp.git && cd comfyui-mcp && python -m venv .venv && source .venv/bin/activate && pip install -e ".[dev]"

What MCP clients work with ComfyUI MCP Server?

ComfyUI MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep ComfyUI MCP Server docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare