# comfy-mcp

> comfy-mcp — cuzelac-comfy-mcp. Use this tool when you need to control a local ComfyUI instance for image generation, enabling workflow understanding, parameter modification, and model discovery. It solves problems related to automating image generation workflows and allows AI agents to execute and modify ComfyUI parameters. The comfy-mcp server accepts input commands from AI agents and outputs generated images and workflow information.

Canonical page: https://skillsregistry.net/skills/cuzelac-comfy-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cuzelac-comfy-mcp

## Description

MCP server that enables AI agents to control a local ComfyUI instance for image generation, allowing workflow understanding, parameter modification, execution, and model discovery.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pyjrcs48u1)
- **Repository:** <https://github.com/cuzelac/comfy-mcp>

## 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": "cuzelac-comfy-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cuzelac-comfy-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cuzelac-comfy-mcp/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