ComfyUI

by joenorton

32 stars

1k downloads

Not rated

GitHub

About

Integrates ComfyUI with WebSocket communication for on-demand image generation, enabling customizable requests with parameters like prompt, width, and height.

Details

Author: joenorton
Repository: joenorton/comfyui-mcp-server
GitHub stars: 32
Downloads: 1,016
License: Apache License 2.0
Categories: Productivity, Developer Tools, Design, AI, Media, Frontend, Infrastructure, Other
Tags: #integration

- Generate images, audio, and video via natural language
- Iterative refinement with regenerate (no re-prompting needed)
- Job management: polling, cancellation, queue status
- Asset identity via (filename, subfolder, type) for reliable follow-ups
- Optional visual feedback for agents with view_image
- Configurable defaults and custom workflow support
- Publishing assets to web projects with deterministic compression

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name ComfyUI

Command (node, npx, python, etc.) python
Arguments
- Argument 1 server.py
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

From the repository

This proves everything is working.

`generate_image`

Generate images (requires prompt)

`generate_song`

Generate audio (requires tags and lyrics)

`regenerate`

Regenerate an existing asset with optional parameter overrides (requires asset_id)

`view_image`

View generated images inline (images only, not audio/video)

`get_queue_status`

Check ComfyUI queue state (running/pending jobs) - provides async awareness

`get_job`

Poll job completion status by prompt_id - check if a job has finished

`list_assets`

Browse recently generated assets - enables AI memory and iteration

`get_asset_metadata`

Get full provenance and parameters for an asset - includes workflow history

`cancel_job`

Cancel a queued or running job

`list_models`

List available ComfyUI models

`get_defaults`

Get current default values

`set_defaults`

Set default values (with optional persistence)

`list_workflows`

List all available workflows

`run_workflow`

Run any workflow with custom parameters

`get_publish_info`

Show publish status (detected project root, publish dir, ComfyUI output root, and any missing setup)

`set_comfyui_output_root`

Set ComfyUI output directory (recommended for Comfy Desktop / nonstandard installs; persisted across restarts)

`publish_asset`

Publish a generated asset into the project's web directory with deterministic compression (default 600KB)

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "comfyui": {
            "env": {},
            "args": [
                "server.py"
            ],
            "command": "python"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "server.py"
    ],
    "command": "python"
}

Macos

{
    "env": [],
    "args": [
        "server.py"
    ],
    "command": "python"
}

Windows

{
    "env": [],
    "args": [
        "server.py"
    ],
    "command": "python"
}

ComfyUI MCP Server

> Generate and refine AI images/audio/video through natural conversation

A lightweight MCP (Model Context Protocol) server that lets AI agents generate and iteratively refine images, audio, and video using a local ComfyUI instance.

You run the server, connect a client, and issue tool calls. Everything else is optional depth.

---

Quick Start (2–3 minutes)

This proves everything is working.

1) Clone and set up

git clone https://github.com/joenorton/comfyui-mcp-server.git
cd comfyui-mcp-server
pip install -r requirements.txt

2) Start ComfyUI

Make sure ComfyUI is installed and running locally.

cd <ComfyUI_dir>
python main.py --port 8188

3) Run the MCP server

From the repository directory:

python server.py

The server listens at:

```

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

generate_image

generate_song

regenerate

view_image

get_queue_status

get_job

list_assets

get_asset_metadata

cancel_job

list_models

get_defaults

set_defaults

list_workflows

run_workflow

get_publish_info

set_comfyui_output_root

publish_asset

Claude Desktop / Cursor

Linux

Macos

Windows

ComfyUI MCP Server

Quick Start (2–3 minutes)

1) Clone and set up

2) Start ComfyUI

3) Run the MCP server

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7

`generate_image`

`generate_song`

`regenerate`

`view_image`

`get_queue_status`

`get_job`

`list_assets`

`get_asset_metadata`

`cancel_job`

`list_models`

`get_defaults`

`set_defaults`

`list_workflows`

`run_workflow`

`get_publish_info`

`set_comfyui_output_root`

`publish_asset`