- A server implementation for integrating ComfyUI with MCP.
⚠️ IMPORTANT: This server requires a running ComfyUI server.- You must either host your own ComfyUI server,
- or have access to an existing ComfyUI server address.
python src/test_comfyui.pymcp dev src/server.py-
Edit
src/.envto set ComfyUI host and port:COMFYUI_HOST=localhost COMFYUI_PORT=8188
- To add new tools, place your workflow JSON files in the
workflowsdirectory and declare them as new tools in the system.
-
text_to_image
- Returns only the URL of the generated image.
- To get the actual image:
- Use the
download_imagetool, or - Access the URL directly in your browser.
- Use the
-
download_image
- Downloads images generated by other tools (like
text_to_image) using the image URL.
- Downloads images generated by other tools (like
-
run_workflow_with_file
-
Run a workflow by providing the path to a workflow JSON file.
# You should ask to agent like this. Run comfyui workflow with text_to_image.json -
example image of CursorAI
-
-
run_workflow_with_json
-
Run a workflow by providing the workflow JSON data directly.
# You should ask to agent like this. Run comfyui workflow with this { "3": { "inputs": { "seed": 156680208700286, "steps": 20, ... (workflow JSON example) }
-
-
Example
mcp.json:{ "mcpServers": { "comfyui": { "command": "uv", "args": [ "--directory", "PATH/MCP/comfyui", "run", "--with", "mcp", "--with", "websocket-client", "--with", "python-dotenv", "mcp", "run", "src/server.py:mcp" ] } } }
- Downloading images to a local folder with
download_imagemay be difficult since the Docker container does not share the host filesystem. - When using Docker, consider:
- Set
RETURN_URL=falsein.envto receive image data as bytes. - Set
COMFYUI_HOSTin.envto the appropriate address (e.g.,host.docker.internalor your server's IP). - Note: Large image payloads may exceed response limits when using binary data.
- Set
# First build image
docker image build -t mcp/comfyui .{
"mcpServers": {
"comfyui": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-p",
"3001:3000",
"mcp/comfyui"
]
}
}
}Also you can use prebuilt image.
{
"mcpServers": {
"comfyui": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-p",
"3001:3000",
"overseer66/mcp-comfyui"
]
}
}
}-
Run the SSE server with Docker:
docker run -i --rm -p 8001:8000 overseer66/mcp-comfyui-sse
-
Configure
mcp.json(change localhost to your IP or domain if needed):{ "mcpServers": { "comfyui": { "url": "http://localhost:8001/sse" } } }
NOTE: When adding new workflows as tools, you need to rebuild and redeploy the Docker images to make them available.