text_to_imageLABSCO SUMMARY
ComfyUI graphs run from the conversation.
Two things make it usable rather than a demo: a workflow can be run straight from JSON without saving a file first, and the generated image is downloadable rather than left as a URL to fetch by hand.
What it is
An MCP server in front of a running ComfyUI instance. Text-to-image returns the image URL; workflows run either from a JSON file in the workflows directory or from JSON supplied inline, and a separate call downloads the result.
What you get
- An image generated from a prompt, returned as a URL
- The image at that URL downloaded
- A saved workflow run by naming its JSON file
- A workflow run from JSON passed directly in the request
- New workflows added by dropping JSON into the workflows directory and declaring them as tools
Requirements
A running ComfyUI server — your own, or one whose address you have — with its host and port set in src/.env; they already point at a ComfyUI running on your own machine. It runs through uv with the mcp, websocket-client and python-dotenv packages.
Setup effort
Build from source — git clone https://github.com/Overseer66/comfyui-mcp-server.git
USE CASES
01
Getting an image without opening ComfyUI
Generate from a prompt, then download the result.
02
Running the graph you already built
Name the workflow JSON file in the workflows directory and run it.
03
Trying a graph you were just handed
Paste the workflow JSON into the call rather than saving it first.
04
Adding a workflow for repeat use
Drop the JSON in the workflows directory and declare it as a tool.
4 tools
Listed in project docs. Your client may show a different list.
download_imagerun_workflow_with_filerun_workflow_with_jsonBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- uv on PATH
- A running ComfyUI server — your own, or one whose address you have — with its host and port set in src/.env
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/Overseer66/comfyui-mcp-server.git
cd comfyui-mcp-serverEdit src/.env and set COMFYUI_HOST and COMFYUI_PORT to your running ComfyUI server (the README's example is localhost and 8188)
Add the configuration under MCP Clients to your client, with the full path of your comfyui-mcp-server clone
MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"comfyui": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH>/MCP/comfyui",
"run",
"--with",
"mcp",
"--with",
"websocket-client",
"--with",
"python-dotenv",
"mcp",
"run",
"src/server.py:mcp"
]
}
}
}PATH/MCP/comfyui is the full path of your comfyui-mcp-server clone — the folder that holds src/server.py.
