P

comfy-mcp-pipeline

...
Created 2/17/2025bylalanikarim

Categories

comfyuimcppipeline

Language:

Python

Stars:

6

Forks:

1

Comfy MCP Pipeline

This is a pipeline wrapper for comfy-mcp-server for Open WebUI.

Prerequisites

  • Open WebUI
  • Open WebUI Pipelines
  • ComfyUI
  • Updated requirements.txt for pipelines server
  • JSON Export of a ComfyUI Workflow API - see sample for reference workflow.json
    • From Comfy UI, select a workflow to export
    • From the top menu, Workflow -> Export (API) -> provide a filename -> Confirm
    • This file will need to be uploaded to the pipeline server

Pipeline Installation and Setup

  • Follow Open WebUI Pipelines documentation to upload the comfy-mcp-pipeline.py to Pipeline server
  • Choose comfy-mcp-pipeline (pipe) from Pipeline Valves
  • Set configuration for the following valves:
    • Comfy Url: Url for your Comfy UI server.
    • Comfy Url External: External Url for your Comfy UI server. Use Comfy Url value if same.
    • Comfy Workflow Json File: path of the workflow JSON file.
    • Prompt Node Id: Id of the text prompt node from workflow JSON file.
    • Output Node Id: Id of the generated image node from the workflow JSON file.
  • If all steps are successfull, you will see Comfy MCP Pipeline in the list of models

Usage

  • Select New Chat and select Comfy MCP Pipeline
  • Enter an image generation prompt and hit send
  • If the setup was successful you should see the generated image
Last updated: 2/19/2025

Publisher info

lalanikarim's avatar

Karim Lalani

Infinidigm LLC
Leander, TX
44
followers
6
following
117
repos

More MCP servers built with Python

apollo-io-mcp-server

MCP server that exposes the Apollo.io API functionalities as tools

By Edward Choh
mcp-openvision

MCP Server using OpenRouter models to get descriptions for images

By Nazruden2
DeepView MCP

Enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini's extensive context window.

By ai-1st