Agent skill

Comfy MCP

by autonomous-ai in autonomous-ai/openharness

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

MITAuto-check passedAgent Workflows

Install Comfy MCP

skills CLI
$ npx skills add autonomous-ai/openharness --skill comfy-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/openharness comfy-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/comfy-mcp/skills/comfy-mcp .claude/skills/comfy-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
comfy-mcp
GitHub stars
1.2k
Token cost
~526 tokens
SKILL.md length
269 words
Files
1
Skills in repo
99
Repo updated
First seen
Licence
MIT

At a glance

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

  • Tasks that involve MCP servers
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Comfy MCP is an agent skill from autonomous-ai/openharness. Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and ComfyUI. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/comfy-mcp”

What it can do on your machine

Read from SKILL.md and the folder at commit 74c2733. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Comfy MCP loads about 526 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 269 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~526

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/openharness at commit 74c2733, republished under its MIT licence (© autonomous-ai). 269 words, ~526 tokens.

Download SKILL.mdSave it as .claude/skills/comfy-mcp/SKILL.md (or your agent's skills folder).
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.

© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in store/agents/comfy-mcp/skills/comfy-mcp of autonomous-ai/openharness.

Open the folder on GitHubat commit 74c2733

Compare with similar skills

Comfy MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Comfy MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comfy MCP this skillautonomous-ai/openharness1.2k—~526Automated safety check: PassMIT
ComfyComfy-Org/comfy-skills219—~1.4kAutomated safety check: PassMIT
Workflow Assistantfilliptm/ComfyUI_FL-MCP127—~3.6kAutomated safety check: PassMIT
Setupguaardvark/guaardvark257—~1.2kAutomated safety check: PassMIT
Panel Node Pack Syncartokun/comfyui-mcp800—~2.9kAutomated safety check: NotesMIT
Report Bugartokun/comfyui-mcp800—~446Automated safety check: PassMIT

Similar skills

  • Comfy

    Comfy-Org/comfy-skills

    Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…

    219 GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Workflow Assistant

    filliptm/ComfyUI_FL-MCP

    A skill your agent uses when working with ComfyUI workflows through FL-MCP or similar MCP tools: inspect, explain, create, edit, debug, compact, validate, queue, screenshot, or organize node graphs…

    127 GitHub stars~3.6k tokensUpdated 25 days ago
    Agent WorkflowsAuto-check passed
  • Setup

    guaardvark/guaardvark

    Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now.

    257 GitHub stars~1.2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Panel Node Pack Sync

    artokun/comfyui-mcp

    Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates.

    800 GitHub stars~2.9k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check: notes
  • Report Bug

    artokun/comfyui-mcp

    Issue reporting is disabled during limited maintenance of comfyui-mcp and the local Agent Panel.

    800 GitHub stars~446 tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Managing MCP Index

    Comfy-Org/workflow_templates

    Builds and maintains templates/index.mcp.json for Comfy Cloud MCP tools.

    1.3k GitHub stars~1.9k tokensUpdated yesterday
    Frontend & DesignAuto-check: notes

More from autonomous-ai/openharness

All 99 skills in this repo
  • G-code Slicer Tool

    autonomous-ai/openharness

    Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Home Assistant Automation Builder

    autonomous-ai/openharness

    Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • OrcaSlicer 3MF and G-code Workflow

    autonomous-ai/openharness

    Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Sheets and Docs Report Builder

    autonomous-ai/openharness

    Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.

    1.2k GitHub stars~708 tokensUpdated today
    Auto-check passed
  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.2k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Comfy MCP

What does Comfy MCP do?

Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration. Comfy MCP is an agent skill from autonomous-ai/openharness. Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.

When should I use Comfy MCP?

Comfy MCP fits situations like: tasks that involve MCP servers.

How do I install Comfy MCP in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill comfy-mcp -a claude-code`. Or copy the skill folder (store/agents/comfy-mcp/skills/comfy-mcp in autonomous-ai/openharness) into .claude/skills/comfy-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Comfy MCP in Codex?

Run `npx skills add autonomous-ai/openharness --skill comfy-mcp -a codex`. Or copy the skill folder (store/agents/comfy-mcp/skills/comfy-mcp in autonomous-ai/openharness) into .agents/skills/comfy-mcp in your project. Codex loads it when a task matches its description.

Can I use Comfy MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill comfy-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comfy-mcp, .gemini/skills/comfy-mcp, .github/skills/comfy-mcp and .opencode/skills/comfy-mcp in your project.

What does Comfy MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Comfy MCP is instructions for the agent only.

Does Comfy MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Comfy MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Comfy MCP use?

Comfy MCP is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Comfy MCP use?

About 526 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Comfy MCP?

Skills that share tags, products or a category with Comfy MCP: Comfy (Comfy-Org/comfy-skills, 219 stars), Workflow Assistant (filliptm/ComfyUI_FL-MCP, 127 stars), Setup (guaardvark/guaardvark, 257 stars) and Panel Node Pack Sync (artokun/comfyui-mcp, 800 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comfy MCP?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,194 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 9, 2026.

Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.