Log inSubmit server
Comfy MCP logo

Comfy MCP

Runs local ComfyUI workflows from MCP-compatible AI clients, with job monitoring, output collection, previews, and workflow inspection.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Comfy MCP

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

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "comfy-mcp": {
      "command": "uvx",
      "args": [
        "comfy-mcp"
      ]
    }
  }
}

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

comfy-mcp connects MCP-speaking clients to a local ComfyUI installation through the comfy-cli command-line engine. It can execute workflow JSON, generate images from prompts, monitor asynchronous jobs, collect outputs, inspect installed nodes and models, and manage the ComfyUI process. Use it when an agent needs to operate your own ComfyUI workspace, or point supported run and job operations at another ComfyUI instance with COMFYUI_URL. Hosted partner-model generation is also available, but this server does not execute workflows on Comfy Cloud.

Use cases

  • Run a ComfyUI workflow from an agent
  • Generate images from text prompts
  • Inspect installed ComfyUI nodes and models
  • Monitor and collect asynchronous job outputs
  • Build workflow variants from templates

Key features

  • Workflow execution from JSON
  • Asynchronous job monitoring and cancellation
  • ComfyUI node, model, and template discovery
  • Media previews for video and audio
  • ComfyUI process and log management
  • Hosted partner-model generation

Security & health

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

ActiveLast checked

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 3h ago via OSV.dev · comfy-mcp (PyPI)

Adoption & maintenance

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

GitHub stars342Stargazers on the source repository.
Last commitTodayMost recent push to the default branch.

How Comfy MCP works

What comfy-mcp does

comfy-mcp exposes a local ComfyUI installation to AI agents through the Model Context Protocol. It is intended for clients such as Claude Code, Claude Desktop, and Cursor. The server can run workflow JSON in API format or from a UI export, create images from text prompts, and return generated files for inspection.

Its capabilities extend beyond execution. Agents can query the nodes, models, and templates available in the connected ComfyUI installation, including custom nodes. They can validate workflow graphs, populate template slots, create workflow variants, and inspect media by converting video to contact sheets or audio to waveforms.

ComfyUI process controls are also exposed: agents can launch, stop, and restart the server, read its logs, and prepare input assets. Partner-model operations can submit work to hosted models such as Flux, Ideogram, or Kling, while partner-API nodes can be used from locally executed workflows.

How it works

The MCP server communicates over stdio. An AI client starts comfy-mcp as a subprocess, and the server invokes the comfy executable for each operation using local targeting and JSON output. The resulting comfy-cli envelope is parsed and returned through MCP.

By default, operations address ComfyUI at 127.0.0.1:8188. COMFYUI_URL can direct run and job operations to another ComfyUI instance under your control. The local server and Comfy Cloud MCP are separate: comfy-mcp runs as a local stdio process, while Comfy Cloud MCP is a remote HTTP service that executes on Comfy Cloud GPUs.

Typical execution uses server_info to check availability, run_workflow to submit a workflow, and fetch_outputs to collect the resulting files. Jobs can also be submitted asynchronously, watched, awaited, cancelled, and checked for failure details.

Setup and configuration

Install the MCP package and the command-line engine separately:

Terminal
pip install comfy-mcp "comfy-cli>=1.14.0"

Create a ComfyUI workspace with comfy install if needed, then start ComfyUI with:

bash
comfy launch

Configure the AI client to launch the comfy-mcp console script, then reload the client so its tools become available. The executable must be discoverable through the client's PATH, or selected explicitly with COMFY_BIN. Installing comfy-mcp alone does not install comfy-cli; the server uses whichever comfy binary it resolves at runtime.

Authentication for Comfy services can use auth_login or COMFY_API_KEY. A separate ComfyUI URL can be supplied through COMFYUI_URL when the target is not the default local address.

Tools and capabilities

  • Run API-format or UI-exported workflow JSON.
  • Generate an image from a text prompt in one call.
  • Submit, wait for, watch, cancel, and inspect asynchronous jobs.
  • Collect generated output files from ComfyUI.
  • Search installed nodes, models, and workflow templates.
  • Validate graphs, edit template slots, and create workflow variants.
  • Produce video contact sheets and audio waveforms for agent inspection.
  • Launch, stop, restart, and inspect ComfyUI through logs.
  • Stage assets for use as workflow inputs.
  • Submit generation requests to supported hosted partner models.

Limitations and notes

The project is marked beta. Its standard execution path depends on a running ComfyUI installation and a working comfy-cli executable. The default target is local; this server is not a gateway to Comfy Cloud and does not provide cloud-hosted execution, cloud queue management, or cross-session cloud batches.

Generated files are written by ComfyUI into the workspace's output/ directory. The fetch_outputs operation can additionally copy outputs to a specified destination. Partner-model requests may run entirely on partner infrastructure rather than through the local ComfyUI process.

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 Comfy MCP

comfy-mcp is an MCP server that connects AI clients to ComfyUI through comfy-cli. Its main tools run workflow JSON, generate images from prompts, monitor and cancel jobs, collect output files, inspect installed nodes and models, and manage the local ComfyUI process. It communicates with clients over stdio.

Install it with `pip install comfy-mcp "comfy-cli>=1.14.0"`, then create or use a ComfyUI workspace and start it with `comfy launch`. Configure your MCP client to launch the `comfy-mcp` console script. The comfy-cli package is installed separately because the server uses the executable resolved at runtime.

Yes, comfy-mcp is documented for Cursor, Claude Code, and Claude Desktop. Configure Cursor to launch the `comfy-mcp` stdio command and reload the client so the MCP tools become available.

Yes, set `COMFYUI_URL` to direct run and job operations to another ComfyUI instance you control. The server remains a local stdio process, and this option does not connect it to Comfy Cloud.

No, comfy-mcp does not execute workflows on Comfy Cloud or provide its cloud queue and cross-session cloud-batch features. Comfy Cloud MCP is a separate remote HTTP server. Partner-model requests are available through this server, but they are not Comfy Cloud execution.

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 PreviewComfy MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/comfy-mcp?style=directory)](https://allmcps.com/mcp/comfy-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/comfy-mcp"><img src="https://allmcps.com/api/badge/comfy-mcp?style=directory" alt="Comfy MCP on AllMCPs" /></a>