$git clone https://github.com/artokun/comfyui-mcpThe local-first, agent-native control plane for [ComfyUI](https://github.com/comfyanonymous/ComfyUI) — an MCP server + live sidebar agent that generates images, video and audio, authors and runs workflows, manages models and custom nodes, and **edits your live ComfyUI graph i
| 1 | # comfyui-mcp — drive ComfyUI with ANY LLM |
| 2 | |
| 3 | **The local-first, agent-native control plane for [ComfyUI](https://github.com/comfyanonymous/ComfyUI)** — an MCP server + live sidebar agent that generates images, video and audio, authors and runs workflows, manages models and custom nodes, and **edits your live ComfyUI graph in natural language**. Bring whatever model you have: **Claude or ChatGPT on your subscription, Gemini on your Google login, a free local model via Ollama (fully offline), or any hosted model over one API key** (DeepSeek, GLM, MiMo, Kimi, GPT, Claude via OpenRouter). Same tools, same panel, every tier — and the built-in [LLM Arena](https://comfyui-mcp.artokun.io/docs/arena) scores them all on real ComfyUI tasks so you know exactly what your model can do. One config targets local installs, LAN, VPS, or Comfy Cloud. |
| 4 | |
| 5 | [](https://www.npmjs.com/package/comfyui-mcp) |
| 6 | [](https://nodejs.org) |
| 7 | [](./LICENSE) |
| 8 | [](https://comfyui-mcp.artokun.io/docs) |
| 9 | |
| 10 | [](https://glama.ai/mcp/servers/artokun/comfyui-mcp) |
| 11 | [](https://glama.ai/mcp/servers/artokun/comfyui-mcp) |
| 12 | |
| 13 | [](https://console.runpod.io/deploy?template=bnqtkvcer3&ref=dkx71w9b) [](https://discord.gg/cW9arBhzCu) **One-click GPU pod** — a ready-to-run ComfyUI with this project + [Agent Panel](https://github.com/artokun/comfyui-mcp-panel) + ComfyUI-Manager v2 preinstalled, on your own GPU. No setup. |
| 14 | |
| 15 | Works on **macOS**, **Linux**, and **Windows**. Auto-detects your ComfyUI installation and port. |
| 16 | |
| 17 | **Stuck or have a question? [Join the Discord](https://discord.gg/cW9arBhzCu)** — help, model tips, and release announcements. |
| 18 | |
| 19 | **108 MCP tools** | **32 AI skills** (Flux · WAN · LTX 2.3 video · Qwen · Z-Image · Ideogram 4 · ERNIE · ANIMA · model registry · Civitai · node authoring · launch/perf flags) | **13 installer packs** | **11 slash commands** | **4 autonomous agents** | **4 hooks** |
| 20 | |
| 21 | The plugin ships **expert skills that grow with every release** — model-specific generation guides with curated download URLs, workflow recipes, troubleshooting, and custom-node authoring — so Claude knows the right sampler, CFG, resolution, and model files for each architecture without trial and error. |
| 22 | |
| 23 | > ### ✅ Now available: the [ComfyUI Agent Panel](https://registry.comfy.org/nodes/comfyui-agent-panel) on ComfyUI-Manager & the Comfy Registry |
| 24 | > An autonomous AI agent in your ComfyUI sidebar — **on Claude, ChatGPT, Gemini, or ANY local/hosted LLM** (Ollama and every OpenAI-compatible endpoint). Subscriptions work with no API key; local models work with no account at all. Pick a provider and it drives your live graph: edits, spatial layout, one-shot workflow/pack loads, rewind/rollback, a pending-message tray, activity cards, multi-tab — and it asks before spending paid API credits. |
| 25 | > Search **`comfyui-agent-panel`** in ComfyUI-Manager to install. [Read more →](https://comfyui-mcp.artokun.io/docs/panel) |
| 26 | |
| 27 | 📖 **Full documentation: [comfyui-mcp.artokun.io/docs](https://comfyui-mcp.artokun.io/docs)** |
| 28 | |
| 29 | --- |
| 30 | |
| 31 | ## Quick Start |
| 32 | |
| 33 | **1. Install ComfyUI** (if you haven't already): [ComfyUI Desktop](https://www.comfy.org/download) or [from source](https://github.com/comfyanonymous/ComfyUI) |
| 34 | |
| 35 | **2. Add the MCP server** to your Claude Code config (`~/.claude/settings.json`): |
| 36 | |
| 37 | ```json |
| 38 | { |
| 39 | "mcpServers": { |
| 40 | "comfyui": { |
| 41 | "co |