Comfy MCP Server

@lalanikarim

Repository

Basic information

About Comfy MCP Server

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

#comfyui #mcp-server

Comfy MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "comfy-mcp-server": {
      "command": "uvx",
      "args": [
        "comfy-mcp-server"
      ]
    }
  }
}

Comfy MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Comfy MCP Server?

Comfy MCP Server uses the FastMCP framework to generate images based on prompts via a remote Comfy server. It submits prompts to a Comfy server and retrieves generated images.

How to use Comfy MCP Server?

Set the required environment variables (COMFY_URL, COMFY_WORKFLOW_JSON_FILE, PROMPT_NODE_ID, OUTPUT_NODE_ID, OUTPUT_MODE) and optionally OLLAMA_API_BASE and PROMPT_LLM. Launch the server with uvx comfy-mcp-server. Configure it in Claude Desktop by adding the command and environment variables to the MCP server configuration.

Key features of Comfy MCP Server

generate_image(prompt, ctx) submits a prompt and returns the generated image.
generate_prompt(topic, ctx) creates an image generation prompt from a topic.
Supports optional Ollama integration for prompt generation.
Works with any exported ComfyUI workflow JSON file.
Outputs images as URLs or local files via OUTPUT_MODE.

Use cases of Comfy MCP Server

Generate images from text prompts using a remote Comfy server.
Automatically enrich a topic into a detailed image-generation prompt via Ollama.
Integrate image generation into MCP clients like Claude Desktop.
Use custom ComfyUI workflows without modifying the server code.

Frequently asked questions

What does the server do?

It generates images by sending prompts to a remote Comfy server and retrieving the results.

What prerequisites are needed?

You need `uv` (Python package manager), a Comfy server URL, and an exported workflow JSON file from ComfyUI.

How do I configure the environment variables?

Set `COMFY_URL`, `COMFY_WORKFLOW_JSON_FILE`, `PROMPT_NODE_ID`, `OUTPUT_NODE_ID`, and `OUTPUT_MODE`. Optionally set `OLLAMA_API_BASE` and `PROMPT_LLM` for prompt generation via Ollama.

Is Ollama required?

No, Ollama is optional. The server can generate images without it, but if Ollama is available it can be used to turn a topic into a detailed prompt.

What output formats are supported?

The server supports two modes via `OUTPUT_MODE`: `url` to return an image URL, or `file` to return the image as a file.

Comments

More Other MCP servers

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep