# ComfyUI

> Use this tool when you need to integrate AI image generation into conversational interfaces, solving the problem of complex workflow management for generating images from text prompts. ComfyUI MCP Server takes in customizable parameters and JSON workflow templates as input, and outputs generated images via URL or binary return. It is ideal for developers seeking to leverage AI-powered image generation in chatbots and virtual assistants without handling underlying complexities.

Canonical page: https://skillsregistry.net/skills/overseer66-comfyui  
JSON: https://api.skillsregistry.net/v1/skills/overseer66-comfyui

## Description

ComfyUI MCP Server provides a bridge between AI assistants and ComfyUI's image generation capabilities. Built with Python, it exposes two main tools: text-to-image generation with customizable parameters (prompt, seed, steps, CFG scale, and denoise strength) and image downloading functionality. The server communicates with ComfyUI via WebSocket connections, processes workflow templates from JSON files, and supports both URL-based and binary image returns. It features Docker support with both standard and SSE transport options, authentication capabilities for secure ComfyUI instances, and environment variable configuration. This implementation is particularly valuable for developers who want to integrate AI image generation into conversational interfaces without managing the complexities of ComfyUI's workflow system directly.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/overseer66-comfyui)
- **Repository:** <https://github.com/overseer66/comfyui-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "overseer66-comfyui"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/overseer66-comfyui` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/overseer66-comfyui/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt