Comfy MCP Server

2 forks

7 stars

Free

What is comfy-mcp-server

comfy-mcp-server is a robust server application developed by lalanikarim that leverages the FastMCP framework. It is designed to generate images based on textual prompts by interfacing with a remote Comfy server. This server acts as a bridge, processing requests to generate images through a specified workflow, thus making it an essential tool for users who require automated image generation from textual descriptions.

The server is part of a broader ecosystem using the Model Context Protocol (MCP), which facilitates secure connections between AI systems and various data sources. comfy-mcp-server is particularly useful for applications where real-time image generation and retrieval are necessary, utilizing the power of AI to transform textual prompts into visual content.

How to Use comfy-mcp-server

To use comfy-mcp-server effectively, follow these steps:

Install Prerequisites: Ensure you have the necessary Python packages, particularly the uv package and project manager.
- Use the command uvx mcp[cli] to install the required packages.
Configure Environment Variables: Set up your environment by defining several key variables:
- COMFY_URL: The URL of your Comfy server.
- COMFY_WORKFLOW_JSON_FILE: The path to your Comfy UI workflow JSON file.
- PROMPT_NODE_ID: The ID for the text prompt node.
- OUTPUT_NODE_ID: The ID for the output node where the final image will be retrieved.
- OUTPUT_MODE: Choose either url or file for your desired output format.
Optionally, configure for an Ollama server if you need enhanced prompt generation capabilities.
Launch the Server: Start the comfy-mcp-server by running the command:
```
uvx comfy-mcp-server
```
Example Configuration: You can create a configuration file for desktop environments like Claude Desktop, specifying the command and environment variables in JSON format.

Key Features of comfy-mcp-server

Image Generation: Automatically generate images from text prompts by interfacing with a remote Comfy server, utilizing a pre-defined workflow.
Flexible Output Options: Choose between URL or file output modes to receive the generated images in the format that suits your application.
Integration with AI Models: Option to connect with an Ollama server for advanced prompt generation, allowing for more sophisticated image creation based on AI-generated prompts.
Environment Configuration: Easily configurable via environment variables, enabling seamless integration into various workflows and systems.
Polling and Retrieval: Efficiently polls the Comfy server to check the status of image generation and retrieves the final output once ready.
Comprehensive Documentation: Although external links are not provided here, the software typically comes with detailed documentation to guide users through setup and operation, ensuring ease of use even for those less familiar with server configurations.

By using comfy-mcp-server, users can harness the power of AI-driven image generation in an automated and efficient manner, making it an invaluable tool for creative projects, automated content creation, and more.

A server using FastMCP framework to generate images based on prompts via a remote Comfy server.

Overview

This script sets up a server using the FastMCP framework to generate images based on prompts using a specified workflow. It interacts with a remote Comfy server to submit prompts and retrieve generated images.

Prerequisites

uv package and project manager for Python.
Workflow file exported from Comfy UI. This code includes a sample Flux-Dev-ComfyUI-Workflow.json which is only used here as reference. You will need to export from your workflow and set the environment variables accordingly. You can install the required packages for local development:

uvx mcp[cli]

Configuration

Set the following environment variables:

COMFY_URL to point to your Comfy server URL.
COMFY_WORKFLOW_JSON_FILE to point to the absolute path of the API export json file for the comfyui workflow.
PROMPT_NODE_ID to the id of the text prompt node.
OUTPUT_NODE_ID to the id of the output node with the final image.
OUTPUT_MODE to either url or file to select desired output. Optionally, if you have an Ollama server running, you can connect to it for prompt generation.
OLLAMA_API_BASE to the url where ollama is running.
PROMPT_LLM to the name of the model hosted on ollama for prompt generation. Example:

export COMFY_URL=
export COMFY_WORKFLOW_JSON_FILE=/path/to/the/comfyui_workflow_export.json
export PROMPT_NODE_ID=6 # use the correct node id here
export OUTPUT_NODE_ID=9 # use the correct node id here
export OUTPUT_MODE=file

Usage

Comfy MCP Server can be launched by the following command:

uvx comfy-mcp-server

Example Claude Desktop Config

 "mcpServers": {
 "Comfy MCP Server": {
 "command": "/path/to/uvx",
 "args": [
 "comfy-mcp-server"
 "env": {
 "COMFY_URL": "
 "COMFY_WORKFLOW_JSON_FILE": "/path/to/the/comfyui_workflow_export.json",
 "PROMPT_NODE_ID": "6",
 "OUTPUT_NODE_ID": "9",
 "OUTPUT_MODE": "file",

Functionality

`generate_image(prompt: str, ctx: Context) -> Image | str`

This function generates an image using a specified prompt. It follows these steps:

Checks if all the environment variable are set.
Loads a prompt template from a JSON file.
Submits the prompt to the Comfy server.
Polls the server for the status of the prompt processing.
Retrieves and returns the generated image once it's ready.

`generate_prompt(topic: str, ctx: Context) -> str`

This function generates a comprehensive image generation prompt from specified topic.

Dependencies

mcp: For setting up the FastMCP server.
json: For handling JSON data.
urllib: For making HTTP requests.
time: For adding delays in polling.
os: For accessing environment variables.
langchain: For creating simple LLM Prompt chain to generate image generation prompt from topic.
langchain-ollama: For ollama specific modules for LangChain.

License

This project is licensed under the MIT License - see the LICENSE file for details.

How to Use

To use the comfy-mcp-server, follow these steps:

Visit https://github.com/lalanikarim/comfy-mcp-serverhttps://github.com/lalani...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using comfy-mcp-server capabilities within your Claude conversations

Additional Information

Created

February 14, 2025

Company

lalanikarim

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More