Borrowing it
Nothing to install: this file belongs to hybridindie/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.
curl -O https://raw.githubusercontent.com/hybridindie/comfyui_mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/hybridindie/comfyui_mcpWrote 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.
[](https://agentmods.dev/instructions/hybridindie/comfyui_mcp/agents-md)<a href="https://agentmods.dev/instructions/hybridindie/comfyui_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hybridindie/comfyui_mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04166 | $0.04166 |
| Opus 5 | $0.02083 | $0.02083 |
| Sonnet 5 | $0.00833 | $0.00833 |
| Haiku 4.5 | $0.00417 | $0.00417 |
Grade A, and why
comfyui_mcp AGENTS.md scanned grade A with 2 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Check the package source for calls to `exec`, `eval`, `subprocess`, `os.system`, `open()`, `requests`, `urllib`, or `httpx` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
1. Check the package source for calls to `exec`, `eval`, `subprocess`, `os.system`, `open()`, `requests`, `urllib`, or `httpx` How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for OpenCode and other agentic clients working in comfyui_mcp.
Independent & harness-agnostic
comfyui_mcp is a standalone MCP server — a secure Model Context Protocol server for ComfyUI. It is usable by any AI agent harness (OpenCode, or any MCP client over stdio or Streamable HTTP) and exposes ComfyUI's workflow / generation / discovery / security API.
It has no dependency on any specific consumer. The server is the product;
the /comfy:* skills shipped in this repo are convenience recipes that wrap
multi-tool flows — they are not coupled to any one harness.
The constitutional rules themselves live in .opencode/rules/,
loaded as instructions in opencode.json, and
are the source of truth for how to build here:
security.md— blocked endpoints, PathSanitizer, rate limiter, audit log, workflow inspector (the non-negotiable security invariants)architecture.md— layout,_build_server(), tool registration contract, Model Manager envelope, dangerous-nodes list maintenancetools.md— the@mcp.tool()contract and the new-tool checklisttesting.md—respxmocks,asyncio_mode = auto, real tool functionsworkflow.md— issue → red test → green → preflight → PR → merge pipeline- the eval-gated change rule (Phase 4 before merge)
enforcement.md— gates, PR checklist, lint/format/type, release & versioninggraphify.md— graphify LLM-extraction policy: always run graphify viascripts/graphify.shso the repo.envis observed
These rules are path-scoped; apply the one(s) matching the files you touch. When a rule and this file disagree, the rule wins.
Project Overview
A secure MCP (Model Context Protocol) server for ComfyUI, built on FastMCP 4. Enables AI assistants to generate images, run workflows, and manage jobs through ComfyUI with built-in security controls:
- Workflow Inspector (detects dangerous nodes like
eval,exec) with user elicitation — enforce mode asks the user to confirm before submitting a flagged workflow - Path Sanitizer (blocks path traversal attacks)
- SecurityMiddleware — centralized rate limiting + entry audit logging
(FastMCP 4
on_call_toolhook) across every tool call - Audit Logger (structured JSON logging with redaction)
- Selective API surface (blocks dangerous endpoints)
- Resources — read-only ComfyUI state the LLM can browse by URI
(
comfyui://models/{folder},comfyui://nodes/installed,comfyui://queue,comfyui://system) - Prompts — reusable workflow-template recipes (txt2img, img2img, inpaint, upscale)
- Dependency injection —
Depends()providers for theclient/audit/inspector/limitersingletons (opt-in per tool module; theregister_*_tools()factory remains valid) - Background tasks (optional) —
TasksExtension(Docket-backed) for long-running workflows over the HTTP transport
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.
- 7d ago First seen · 305 lines · 4,166 tokens per session scan A 8f7fef828c7b
comfyui_mcp AGENTS.md is an instructions file published in the GitHub repository hybridindie/comfyui_mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 4,166 tokens to every session, about $0.0208 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
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.