comfyui-mcp: Instructions file for Claude Code

CLAUDE.md

comfyui-mcp CLAUDE.md is an instructions file for Claude Code from shawnrushefsky/comfyui-mcp. It costs 1,475 tokens per session, scanned A, original, MIT.

Project instructions for a TypeScript MCP server that lets AI assistants interact with ComfyUI, a node-based tool for generating images, audio, and video. They describe its architecture, automatic instance discovery, capability detection, workflow building, and related tools.

In plain words
What is it for?
Use them when developing or reviewing the ComfyUI MCP server, including its REST and WebSocket clients, workflow builder, generation tools, model handling, queue, and installation features.
Why use it?
They help an agent understand how the server connects to ComfyUI and where its main components live. This reduces guesswork when working on generation, queues, models, installation, or progress tracking.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is shawnrushefsky/comfyui-mcp's own configuration. It tells Claude Code how to work on comfyui-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything comfyui-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shawnrushefsky/comfyui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shawnrushefsky/comfyui-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shawnrushefsky/comfyui-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for comfyui-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shawnrushefsky/comfyui-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/shawnrushefsky/comfyui-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shawnrushefsky/comfyui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnrushefsky/comfyui-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for comfyui-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shawnrushefsky/comfyui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnrushefsky/comfyui-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,475 This file is loaded in full into every session.
When invoked 1,475 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01475 $0.01475
Opus 5 $0.00737 $0.00737
Sonnet 5 $0.00295 $0.00295
Haiku 4.5 $0.00147 $0.00147

Measured 10d ago against content hash ebcf8d2c03dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

comfyui-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - ComfyUI MCP Server

Project Overview

This is a TypeScript MCP (Model Context Protocol) server that enables AI assistants to interact with ComfyUI for generating images, audio, and video. The server is designed to be self-configuring, automatically discovering ComfyUI instances and their capabilities.

Architecture

src/
├── index.ts                 # Main MCP server entry point
├── config.ts                # Configuration management
├── context.ts               # Server context (shared state)
├── client/
│   ├── comfyui.ts          # REST API client for ComfyUI
│   └── websocket.ts        # WebSocket client for progress tracking
├── discovery/
│   └── index.ts            # Auto-discovery of ComfyUI instances
├── capabilities/
│   └── index.ts            # Capability detection from object_info
├── workflows/
│   └── builder.ts          # Dynamic workflow generation
├── tools/
│   ├── generate.ts         # Sync workflow execution
│   ├── generate-async.ts   # Async workflow execution
│   ├── models.ts           # Model/node listing and building
│   ├── queue.ts            # Queue management tools
│   ├── install.ts          # Installation assistance
│   ├── validation.ts       # Workflow validation
│   ├── svg.ts              # SVG rendering to PNG
│   ├── fonts.ts            # Font download and management
│   └── examples/           # Example workflows and templates
│       ├── index.ts        # Main exports
│       ├── data.ts         # Aggregated example data
│       ├── types.ts        # Type definitions
│       ├── list-examples.ts # list_examples tool
│       ├── templates.ts    # Template system (search/get/save)
│       ├── recommend.ts    # Workflow recommendations
│       ├── downloads.ts    # Model download URLs
│       ├── basics.ts       # Basic workflow examples
│       ├── flux.ts         # Flux model examples
│       ├── sdxl.ts         # SDXL examples
│       ├── sd3.ts          # SD3 examples
│       ├── controlnet.ts   # ControlNet examples
│       ├── video.ts        # Video generation examples
│       ├── audio.ts        # Audio generation examples
│       ├── hunyuan.ts      # Hunyuan examples
│       ├── next-gen.ts     # Next-gen model examples
│       └── 3d.ts           # 3D generation examples
├── jobs/
│   ├── manager.ts          # Async job tracking
│   └── notifications.ts    # MCP notification handling
├── db/
│   └── index.ts            # SQLite database for notes/templates
├── handlers/
│   ├── resources.ts        # MCP resource handlers
│   └── prompts.ts          # MCP prompt handlers
├── resources/
│   └── prompting-guide.ts  # Model-specific prompting guides
├── analysis/
│   ├── outputs.ts          # User output history analysis
│   └── hash.ts             # Workflow hashing
└── utils/
    ├── image.ts            # Image processing utilities
    └── logging.ts          # MCP logging utilities

Read the full file on GitHub · 150 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 150 lines · 1,475 tokens per session scan A ebcf8d2c03dd

Subscribe to this mod's changes

comfyui-mcp CLAUDE.md is an instructions file published in the GitHub repository shawnrushefsky/comfyui-mcp (18 stars, last pushed 7mo ago), licensed MIT. It adds 1,475 tokens to every session, about $0.0074 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens