comfyui-mcp: Instructions file for Claude Code

CLAUDE.md

comfyui-mcp CLAUDE.md is an instructions file for Claude Code from bernardogv/comfyui-mcp. It costs 1,424 tokens per session, scanned A, original, MIT.

Instructions for developing and testing an MCP server that gives a coding agent 16 tools for controlling ComfyUI on a remote GPU computer. ComfyUI is a tool for building image-generation workflows.

In plain words
What is it for?
Use them to queue ComfyUI workflows, inspect generated outputs, read and write workflow files, download models, and run tests or live smoke checks.
Why use it?
They explain how to build the server, connect it to the GPU machine, run offline tests, and perform a live connection check. This reduces setup mistakes when changing or troubleshooting the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is bernardogv/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 bernardogv/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/bernardogv/comfyui-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bernardogv/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/bernardogv/comfyui-mcp/claude-md.svg)](https://agentmods.dev/instructions/bernardogv/comfyui-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bernardogv/comfyui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bernardogv/comfyui-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,424 This file is loaded in full into every session.
When invoked 1,424 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 $0.01424 $0.01424
Opus 5 $0.00712 $0.00712
Sonnet 5 $0.00285 $0.00285
Haiku 4.5 $0.00142 $0.00142

Measured 6d ago against content hash 0f86c1f6fd96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 6d 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

comfyui-mcp

TypeScript MCP server (stdio) giving Claude Code 16 tools to drive ComfyUI on the spark DGX box — queue workflows, see outputs as MCP image blocks, iterate without the web UI.

Run / test

  • npm run build — tsc to dist/. dist/index.js is what Claude Code runs (registered as the comfyui server in ~/.claude.json). Rebuild after every src change; restart Claude Code to pick it up.
  • npm test — node test runner via tsx (tests/*.test.ts + tests/tools/*.test.ts), all offline (handlers take injectable deps).
  • npm run smoke -- --live — hits spark for real (system_stats, ssh ping, output listing). Without --live it exits immediately.

Connection to spark

All defaults live in src/config.ts, overridable by env (set in the ~/.claude.json server entry):

  • COMFYUI_HOSThttp://<gpu-host>:8188 (HTTP for queue/view/history/stats)
  • SPARK_SSH_ALIASspark (from ~/.ssh/config; SSH for workflow JSON r/w, output listing, model downloads via remote aria2c, comfyscript execution)
  • SPARK_COMFYUI_ROOT — the ComfyUI checkout on the GPU host; SPARK_COMFYUI_PYTHON — the comfyui venv python; LLAMASWAP_HOST — the llama-swap endpoint for the GPU-yield handshake
  • CIVITAI_API_TOKEN / HF_TOKEN — optional, for gated model downloads. Never hardcode.

Tool surface (16 tools, one file per group in src/tools/)

  • stats.tssystem_stats (RAM/VRAM, version, queue size)
  • viewing.tslist_outputs, view_image, view_latest
  • editing.tslist_workflows, read_workflow, write_workflow
  • queueing.tsqueue_workflow (overrides: prompt/negative/checkpoint/seed/steps/cfg/guidance/sampler/scheduler/width/height/loras), get_progress, cancel_queue
  • wait.tswait_for_image; batch.tsqueue_batch (max 8 parallel variants)
  • models.tslist_models, download_model (Civitai + HF via remote aria2c)
  • curate.tspick_top (copy winners to a named folder on spark + scp to ~/Pictures/<folder>/)
  • comfyscript.tsrun_comfyscript

Read the full file on GitHub · 50 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. 6d ago First seen · 50 lines · 1,424 tokens per session scan A 0f86c1f6fd96

Subscribe to this mod's changes

comfyui-mcp CLAUDE.md is an instructions file published in the GitHub repository bernardogv/comfyui-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 1,424 tokens to every session, about $0.0071 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

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