MCP.Market

Comfyui MCP server

by miller-joe·io.github.miller-joe/comfyui-mcp·v0.2.1·1 stars

MCP server for ComfyUI: text-to-image, variations, img2img refine, upscale, image proxy.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

1 stars122 downloads/wk

Reviews

Write one

Nobody has reviewed Comfyui yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Comfyui tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan21 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 112 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Comfyui compares

Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 65% of 1,337 Media servers
GitHub stars
1
more than 55% of 711 Media servers
Downloads a week
122
more than 67% of 358 Media servers with a package

Install Comfyui in Claude Code, Cursor or VS Code

Runs npx -y @miller-joe/comfyui-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add comfyui-mcp -- npx -y @miller-joe/comfyui-mcp
Add to Cursor

What the publisher says

From the Comfyui repository's README, as published. We do not edit it. Read it on GitHub

comfyui-mcp

MCP server for ComfyUI. Generate images from natural language prompts in any MCP-compatible client.

Status

v0.2 ships the core tools plus upscale, an image proxy, and public-URL support. Current tool surface: generateimage, generatevariations, generatewithworkflow, refineimage, upscaleimage, listmodels, listworkflows, uploadimage, generatewithcontrolnet, generatewithipadapter, plus a workflow template registry. See Roadmap for what's next.

Install

npx (no install required)

npx @miller-joe/comfyui-mcp --comfyui-url http://your-comfyui-host:8188

npm

npm install -g @miller-joe/comfyui-mcp
comfyui-mcp --comfyui-url http://your-comfyui-host:8188

Docker

docker run -p 9100:9100 \
  -e COMFYUI_URL=http://your-comfyui-host:8188 \
  ghcr.io/miller-joe/comfyui-mcp:latest

Connect an MCP client

Claude Code:

claude mcp add --transport http comfyui http://localhost:9100/mcp

Or register the streamable HTTP endpoint with an MCP gateway (e.g. MetaMCP) to aggregate with other servers.

Configuration

All options can be set via CLI flag or environment variable:

Transports

The server speaks streamable HTTP by default (great for Claude Code, MetaMCP, raw fetch). Pass --stdio (or set MCP_TRANSPORT=stdio) to switch into stdio mode, which is what stdio-first clients like Claude Desktop and the MCP Inspector expect:

# Claude Desktop config (claude_desktop_config.json):
{
  "mcpServers": {
    "comfyui": {
      "command": "npx",
      "args": ["-y", "@miller-joe/comfyui-mcp", "--stdio", "--comfyui-url", "http://127.0.0.1:8188"]
    }
  }
}

Image URLs returned to clients

Generation tools return image URLs like /view?filename=…. If --comfyui-public-url is not set, URLs use the internal --comfyui-url value.

The server also exposes a proxy endpoint: GET /images/?subfolder=&type=output streams the image bytes through this server, which is useful when clients can reach the MCP server but not ComfyUI directly.

The default checkpoint must match a file in your ComfyUI models/checkpoints/ directory. Override via COMFYUIDEFAULTCKPT or pass checkpoint as a tool argument.

Tools

generate_image

Generate an image from a text prompt using ComfyUI's default txt2img workflow.

Parameters: prompt (required), negative_prompt, width, height, steps, cfg, seed, checkpoint.

generate_variations

Generate multiple variations of the same prompt by varying the seed. Returns all images at once.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Comfyui: common questions

Is Comfyui MCP server safe?
Mostly: it is graded B (82/100). Read the Comfyui safety report
How do I install Comfyui?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Comfyui need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Comfyui maintained?
The last commit was 147 days ago (2026-06-08). The latest release is v0.2.1.
What can I use instead of Comfyui?
Servers from other publishers that do the same job: NovelAI Image MCP server, three.ws for Grok MCP server and Free the Tools MCP server.
How does Comfyui compare with other Media MCP servers?
safety score 82/100 (higher than 65% of 1,337 Media servers); github stars 1 (more than 55% of 711 Media servers); downloads a week 122 (more than 67% of 358 Media servers with a package). Full comparison.

Alternatives to Comfyui

Same job from other publishers: the closest match first, then the best rated.

  • NovelAI Image MCP
    NovelAI image generation as MCP tools: txt2img, img2img, inpaint, upscale, Director, ControlNet.
    B
  • three.ws for Grok
    Free text/image to 3D for Grok Bot, plus your three.ws agents once signed in. Never spends.
    B
  • Free the Tools
    Local PDF, image, data and text tools for AI assistants. Files stay on your computer.
    A
  • PopNow
    AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.
    A
  • Remove AI Watermarks
    Identify and remove AI watermarks and provenance metadata from your own images and video.
    A

More from miller-joe →