No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SlavaSexton · MCP Server · ★ 91
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ComfyUI-Agent-Kit safe to install? View the security audit →
ComfyUI-Agent-Kit The signature ComfyUI skill for AI coding agents: Claude Code, Codex, Gemini CLI, and Qwen Code. By AI VFX NEWS. Make your AI coding agent drive a local ComfyUI at full power, generate images, video, and audio, build and run workflows, and show the graph live in your own ComfyUI canvas, then hand the whole setup to someone else with one command. This is the portable, machine-independent, multi-agent version of a working ComfyUI setup. One shared core (the knowledge + the MCP driver) plus a thin adapter per agent. Clone it, run the installer, and each of your agents gets the same stack, wired to your hardware. GLM (z.ai) run through Claude Code is covered by the adapter. See docs/AGENTS.md for how each agent connects. What it can do Drive ComfyUI from four agents (Claude Code, Codex, Gemini CLI, Qwen Code) off one shared core. GLM via Claude Code is covered too. (docs/AGENTS.md) 90-tool MCP driver.
| Stars | 91 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 63.2482051460531/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-03 |
| Created | 2026-06-20 |
| Platforms | claude-code, cli, codex, gemini, mcp, python |
| Est. Tokens | ~18k |
These tools work well together with ComfyUI-Agent-Kit for enhanced workflows:
Looking for a ComfyUI-Agent-Kit alternative? If you're comparing ComfyUI-Agent-Kit with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Co
MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agen
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch
Explore other popular mcp server tools:
ComfyUI-Agent-Kit is One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and M. It is categorized as a MCP Server with 91 GitHub stars.
ComfyUI-Agent-Kit is primarily written in Python. It covers topics such as ai-art, anthropic, claude.
You can find installation instructions and usage details in the ComfyUI-Agent-Kit GitHub repository at github.com/SlavaSexton/ComfyUI-Agent-Kit. The project has 91 stars and 9 forks, indicating an active community.
ComfyUI-Agent-Kit is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ComfyUI-Agent-Kit on Agent Skills Hub include ComfyUI_Skills_OpenClaw, comfy-pilot, llmio. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: