Comfyui MCP plugin for Grok Build
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
How to install Comfyui MCP in Grok Build
1. Add this repo as a plugin marketplace in Grok Build (once per computer):
grok plugin marketplace add artokun/comfyui-mcp2. Install the plugin:
grok plugin install comfy@artokun/comfyui-mcp --trustReview before you trust it. --trust lets this plugin's hooks, MCP servers and scripts run code on your computer. It's a community repo that neither xAI nor GrokStacks has reviewed, so read its code first.
Then start a new Grok session, or press r in /plugins, to load it.
Inside Grok Build: type /plugins, open the Marketplace tab, press a and add artokun/comfyui-mcp, then select comfy and press i.
Command format: Grok Build's plugin guide
Skills work, MCP part needs manual setup. Grok loads Comfyui MCP's skills and commands, but not its MCP server: it needs settings that Claude Code asks for when you install it (userConfig), and Grok doesn't ask for them. Add the server yourself:
grok mcp add comfyui -e CIVITAI_API_TOKEN= node -- '${CLAUDE_PLUGIN_ROOT}/scripts/launch-server.mjs' --fullSet the variable shown in ${…} in your shell before starting Grok (Grok fills it in when it loads the server).
Then start a new session or press r in /mcps. If it asks you to sign in, select it in /mcps and press i.
What we checked: on Oct 18, 2026 it installed with grok 1.0.62 and Grok found 52 skills, 11 slash commands, 1 subagent. That's an install check only: we haven't run it in a live Grok session.
What it contains
Skills (25)
ai-toolkit-trainer— Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prepanima-base— Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNetanima-lora-trainer— Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the result in the anima-base workflowcivitai— Discover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the officicolor-correction— Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a contact sheet. Covers the "washed out" scomfyui-core— Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usagecomfyui-frontend-extensions— Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), typed events, and handles. Use when writing or editing ComfyUI web-UI extencomfyui-launch-flags— Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big texcomfyui-node-registry— Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CIdebug-render— Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents/masks/preprocessor maps, localize the first bad stage, then fix. Use wdirector— Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenationernie-image— Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multflux-txt2img— Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patternsideogram-ultra— Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompinstaller-packs— Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and tells you to invite the user to contribute new packrea2-identity-edit— Swap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background. Use for "put this jacket on her", "change his shirt", "clothes swap", "try on", "outfit transfer", "virtual try-on", "dress her in", "wear tkrea2-txt2img— Build Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON promptinglocal-llm-free— Run the ComfyUI agent locally for FREE with no subscription, no API key, and fully offline, using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama. Use when the user asks about running locally, running for free, offlinelora-manager— Author ComfyUI-LoRA-Manager nodes from the panel. Use when adding a LoRA Manager loader, stacker, prompt, or text node, or when panel_add_node refuses AUTOCOMPLETE_TEXT_LORAS / AUTOCOMPLETE_TEXT_PROMPT after waiting for a widget.ltx-director— Drive the LTX Director (Timeline) node. Its Add Image/Text/Audio buttons are DOM-only and cannot be clicked by an agent; edit the hidden timeline_data JSON widget instead. Load when a workflow contains LTXDirector / LTXDirectorGuide / Prompltxv2-video— Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base modelsminimax-h3-video— Build MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for 8GB VRAM, 15-second stereo-audio clips, and the official MiniMax prompting guides (cite by link, do not copy).model-compatibility— Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video modelsmodel-registry— Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text encoders, and LoRAs. Use when downloading modelpanel-node-pack-sync— Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (install_comfyui (action:"self_update"), npm i -g comfyui-mcp, a new
Subagents (4)
comfy:comfy-debugger— Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitionscomfy:comfy-explorer— Explores ComfyUI custom node packs and generates complete skillscomfy:comfy-optimizer— Analyzes ComfyUI workflows for performance issues and suggests optimizationscomfy:comfy-researcher— Discovers and ranks ComfyUI custom node packs for a stated image-generation problem
Hooks (1)
hooks— PostToolUse, PreToolUse
About this listing
Comfyui MCP is a community plugin on GitHub by artokun, written as a Claude Code plugin that Grok Build installs. We install-checked it in Grok; we haven't run it in a live session or reviewed its code. When we installed it, Grok found 25 skills, 4 subagents, 1 hook. Its license is MIT. We checked commit 6996d06ff511. It's one of 143 listings in the Design category on GrokStacks.
Stacks Weekly: every new Grok Build and Codex plugin, every Tuesday.
One short email for GrokStacks and CodexStacks readers, with each new plugin's install line and what it ships. Subscribe and get the free starter list: 20 Grok Build plugins worth installing first.
You'll get a confirmation email first. Unsubscribe anytime.
Comfyui MCP FAQ
How do I install Comfyui MCP in Grok Build?
Add the repo as a marketplace with grok plugin marketplace add artokun/comfyui-mcp, then run grok plugin install comfy@artokun/comfyui-mcp --trust. Then start a new Grok session, or press r in /plugins, to load it.
Is Comfyui MCP an official Grok Build plugin?
No. Comfyui MCP is a community plugin on GitHub by artokun, not in xAI's official Grok Build marketplace. We checked that it installs and what Grok loads from it, but haven't run it in a live Grok session or reviewed its code.
What does Comfyui MCP include?
According to what Grok loaded in our install check, Comfyui MCP includes 25 skills, 4 subagents, 1 hook: ai-toolkit-trainer, anima-base, anima-lora-trainer, civitai, color-correction, comfyui-core….
Details
- Type
- Plugin
- Category
- Design
- Source
- Community Claude Code plugin, installs in Grok
- License
- MIT
- Author
- artokun
- Keywords
- agent-skills, ai-agent, claude-code, claude-plugin, comfyui, comfyui-extension, comfyui-mcp-server, flux, image-generation, local-first, mcp
- Source repo
- https://github.com/artokun/comfyui-mcp
- Checked commit
6996d06ff511- Homepage
- https://comfyui-mcp.artokun.io/docs
- Checked by GrokStacks
- Install-checked in Grok Build on Oct 18, 2026; not run in a live session
Something wrong or missing? Submit or improve this listing. Marketplace listings also refresh automatically every night.
For maintainers: badge and embeds
Maintain Comfyui MCP? Add the badge; it links to this page.
Markdown
[](https://grokstacks.com/p/comfyui-mcp/)HTML
<a href="https://grokstacks.com/p/comfyui-mcp/"><img src="https://grokstacks.com/badge.svg" alt="Listed on GrokStacks" width="164" height="28"></a>Embed card (static HTML and inline CSS, no JavaScript). Preview:
<a href="https://grokstacks.com/p/comfyui-mcp/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #2a2e3c;border-radius:12px;background:#0a0b0f;color:#e8eaf0;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#e8eaf0">Comfyui MCP</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 25 skills, 4 subagents, 1 hook</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>Markdown summary
**[Comfyui MCP on GrokStacks](https://grokstacks.com/p/comfyui-mcp/)**: Community plugin for Grok Build with 25 skills, 4 subagents, 1 hook. Install: `grok plugin install comfy@artokun/comfyui-mcp --trust` (after `grok plugin marketplace add artokun/comfyui-mcp`)More on badges, embeds and keeping your listing up to date: GrokStacks for plugin authors.
Also in Design
3dicon
One prompt in, a looping animated 3D icon out — with real transparency. A Claude Code skill.
3dviz Pro Max
Agent skill for creative 3D visualization: turn an idea into a Three.js/Blender scene worth exploring. Claude Code + Codex plugin, 223 recipes, 440 knowledge records, 22 proved kits, 37 runnable studies.
Adobe Premiere Pro MCP
Adobe Premiere Pro MCP. Tools for AI-driven video editing via MCP, for Codex, Claude, and other MCP clients.
Agent Sprite Forge
Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.
Agent Storyboard
本地优先的 Agent 视频分镜工作台：让 Codex、Claude Code 通过 MCP 写分镜、生成图片/视频素材和配音，并自动回填。Local-first storyboard workbench for AI agents (Codex, Claude Code).
AI Business Skills
138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.