Skip to content
Back to skills

Comfy Mcp

ASecurity

Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.

  • 1,124 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agentsnodeapi

Works with

  • api
  • mcp

Security analysis

A100/100

Scanned September 19, 2026

npx -y skills add autonomous-ai/openharness --skill comfy-mcp --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Comfy Mcp?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Comfy Mcp
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/autonomous-ai-comfy-mcp/badge)](https://www.skillsdirectory.com/skills/autonomous-ai-comfy-mcp)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: comfy-mcp
description: Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.
---

# Variation garden

Read `studio.json` to understand the current controls; `"$STUDIO_TOOLCHAIN/../studio.config.json"`
describes their ranges. Run `"$STUDIO_TOOLCHAIN/run.sh" generate` to make a new result.
Successful artifacts and their measurements are in `out/runs/<id>/`; `out/latest.json` names the
current result. A failed run preserves the last success and records the error in the verdict.

The local starter creates deterministic procedural SVG artwork and a contact sheet. It is not diffusion or an AI-generated image claim. The native action submits the saved API workflow to an existing local ComfyUI, polls its result, and collects actual output images. The supplied native workflow uses no model and no paid API.

Use `"$STUDIO_TOOLCHAIN/../README.md"` for the integration contract and commands. Read the relevant
files under `$STUDIO_UPSTREAM` before using an upstream API. Keep controls within their documented
ranges, preserve the data needed to reproduce a comparison, and distinguish preview results from
native service or hardware output. The viewer supports history and artifact downloads; tell the
user which run contains the result, and what was actually measured.

## Grow a reproducible family

Choose a palette and seed, run `generate`, then inspect each study and its saved recipe.
The SVG hashes verify reproducibility. These local vector studies do not use a diffusion
model. Keep selected studies and their seed/parameters together when making a new family.

For an installed ComfyUI, read `$STUDIO_UPSTREAM/README.md` and its `src/` tools before
using the MCP workflow. Save API-format nodes in workspace `workflow.json`. The supplied
EmptyImage/SaveImage workflow needs no model weights. Run `comfy` against loopback
`COMFYUI_URL`, inspect its job history, and retain the returned PNGs. A timeout means the
remote queue may still be running; inspect it before resubmitting expensive work.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…