Log inSubmit server
Comfyui MCP logo

Comfyui MCP

Controls ComfyUI through MCP to build workflows, run jobs, manage models, inspect hardware, and generate media.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Comfyui MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "comfyui-mcp-2": {
      "command": "npx",
      "args": [
        "-y",
        "comfyui-mcp@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

comfyui-mcp connects AI clients to ComfyUI for authoring, editing, visualizing, and executing workflows across image, video, and audio tasks. It exposes queue controls, model and custom-node management, system statistics, VRAM cleanup, workflow library operations, and model discovery through MCP tools. The package runs locally by default, can reach LAN, VPS, RunPod, reverse-proxied, or Comfy Cloud deployments, and supports stdio or authenticated Streamable HTTP. Reach for it when an agent needs to operate a ComfyUI installation rather than only submit a prompt.

Use cases

  • Generate images from natural-language prompts
  • Build and modify ComfyUI workflow graphs
  • Manage models and custom-node packs
  • Inspect queue jobs and diagnose workflow state
  • Free VRAM between model runs

Key features

  • Template-based workflow creation and graph editing
  • Queue inspection, reordering, editing, and cancellation
  • Model search, downloading, inventory, and path management
  • Workflow visualization, analysis, and provenance locks
  • GPU, VRAM, OS, and Python system diagnostics
  • Local stdio and authenticated Streamable HTTP modes

Tools13

What Comfyui MCP lets your agent do. Expand a tool for its parameters.

Self-reported~700 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

24/28 checks healthy over the last 91d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · comfyui-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars897Stargazers on the source repository.
npm downloads72kPackage downloads in the last 30 days.
Last commit5d agoMost recent push to the default branch.
Tools exposed13Callable tools this server registers over MCP.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Comfyui MCP works

What comfyui-mcp does

comfyui-mcp gives MCP-compatible clients a control layer for ComfyUI. It can create workflows from templates, modify graphs node by node, validate them, submit jobs, inspect queue state, and return workflow or system information. Supported workflow templates include text-to-image, image-to-image, upscaling, inpainting, ControlNet, IP-Adapter, ACE Step 1.5, and Stable Audio 3.

The server also manages the surrounding ComfyUI environment. Agents can inspect installed models and search the ComfyUI Registry for custom-node packs, upload local input images, download model files, adjust model paths, clear cached VRAM, and examine GPU, operating-system, Python, and VRAM details. Workflow files can be listed, analyzed, queried, stripped of virtualized content, saved, and checked against provenance locks.

How it works

The default launch method uses the npm package through npx and communicates over MCP stdio. ComfyUI must be running; the server auto-detects a local installation and its port. The same configuration can target a self-hosted instance on macOS, Linux, or Windows, as well as remote installations reached over a LAN, VPS, RunPod, or reverse proxy.

For remote MCP clients, --tunnel switches to authenticated Streamable HTTP, starts a Cloudflare quick tunnel, and prints a URL, token, and connector configuration. Plain HTTP is also available, while authentication can be enabled with an HTTP token. A community cloud mode is available through a ComfyUI API key.

Setup and configuration

Install ComfyUI from ComfyUI Desktop or from source, then register the server in the MCP client configuration. A minimal stdio entry runs npx -y comfyui-mcp; the package does not require cloning the repository. Node.js 22 or newer is required.

The example configuration includes CIVITAI_API_TOKEN, which enables authenticated Civitai operations when needed. Cloud deployments use COMFYUI_API_KEY, and HTTP authentication can be configured with COMFYUI_MCP_HTTP_TOKEN. These settings are only needed for the corresponding features or deployment modes.

The project also ships a Claude Code plugin. Installing it adds commands such as generation, workflow visualization, debugging, batching, format conversion, custom-node installation, and gallery browsing on top of the MCP tools.

Tools and capabilities

  • Queue, inspect, edit, reorder, and cancel ComfyUI jobs.
  • Build, modify, validate, render, and convert workflow graphs.
  • Read, save, analyze, query, and provenance-lock workflow files.
  • Upload input images for image-to-image, inpainting, and ControlNet workflows.
  • Search for models through Hugging Face and Civitai, download them, track transfers, and resolve missing files.
  • List, remove, and locate local checkpoints, LoRAs, VAEs, ControlNet models, embeddings, CLIP files, UNets, diffusion models, text encoders, and upscalers.
  • Search registry custom-node packs and inspect loaded node classes through the Comfy CLI.
  • Inspect hardware, clear cached VRAM, and assess or apply comfy-kitchen optimization paths.

Limitations and notes

The primary target is a running self-hosted ComfyUI installation, even though remote and cloud deployment modes are supported. Model removal deletes a model file, so that operation should be used deliberately. The default local stdio setup stays unauthenticated; public HTTP deployments should use the provided token-based authentication. Cloudflare quick-tunnel operation depends on the cloudflared executable and a reachable deployment environment.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Comfyui MCP

comfyui-mcp is an MCP server that connects AI clients to ComfyUI. Its main tools create, edit, validate, visualize, save, and run workflows, while also managing queues, models, custom nodes, uploaded images, VRAM, and system diagnostics. It targets local or remotely reachable ComfyUI installations.

Install ComfyUI, then add `npx -y comfyui-mcp` as an MCP server command in your client configuration. Node.js 22 or newer is required, and the package can be fetched and run by npx without cloning the repository.

Yes, comfyui-mcp works with Claude Code as both an MCP server and a plugin. The plugin adds slash commands, skills, agents, and hooks for generation, visualization, debugging, batching, workflow conversion, custom-node installation, and gallery browsing.

Yes, it can reach ComfyUI on a LAN, VPS, RunPod, reverse proxy, or supported cloud deployment. Use the remote HTTP mode or run `npx -y comfyui-mcp@latest --tunnel` to create an authenticated Streamable HTTP endpoint and receive connector details.

Use the model tools to list installed files, inspect search paths, add or remove paths, search Hugging Face or Civitai, download weights, track transfers, and resolve missing models. Removing a model deletes its file, so it should be treated as a destructive operation.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewComfyui MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/comfyui-mcp-2?style=directory)](https://allmcps.com/mcp/comfyui-mcp-2)
HTML Embed
<a href="https://allmcps.com/mcp/comfyui-mcp-2"><img src="https://allmcps.com/api/badge/comfyui-mcp-2?style=directory" alt="Comfyui MCP on AllMCPs" /></a>