Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Comfy-Org/workflow_templatesnpx agentmods add skills/comfy-org/workflow_templates/managing-mcp-indexWrote 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/skills/comfy-org/workflow_templates/managing-mcp-index)<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/managing-mcp-index"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-mcp-index/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.
<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/managing-mcp-index"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-mcp-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00172 | $0.01971 |
| Opus 5 | $0.00086 | $0.00986 |
| Sonnet 5 | $0.00034 | $0.00394 |
| Haiku 4.5 | $0.00017 | $0.00197 |
Grade A, and why
managing-mcp-index 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing MCP Index
What This Is
templates/index.mcp.json is a machine-oriented template index for Comfy Cloud MCP tools. It is separate from:
| System | File(s) | Purpose |
|---|---|---|
| MCP index (this skill) | index.mcp.json |
English metadata for AI tool routing: description, io, capabilities, recommend |
| Hub manifest | index.json + index.{locale}.json |
Human UI + 11-language titles/descriptions → skill: managing-translations |
| Site SEO | site/ AI pipeline |
Long-form page copy → skill: regenerating-ai-content |
MCP descriptions are English only. There is no MCP translation step. Multi-language hub copy uses npm run i18n (sync_data.py), not the MCP pipeline.
Quick Commands (npm)
npm run mcp # Step 1: sync index.json → index.mcp.json
npm run mcp:check # Dry-run sync (no write)
npm run mcp:ai # Step 2b: AI English descriptions (stale templates only)
npm run mcp:models # Step 2a: AI model profiles in models_registry.json
npm run mcp:enhance # Step 2a + Step 2b in the required order
npm run i18n # Hub translations (NOT MCP — separate system)
Prerequisites for AI steps: copy .env.example → .env, set AI_API_KEY, AI_BASE_URL, AI_MODEL. Optional: COMFYUI_REPO_PATH for API node dropdown scanning during npm run mcp.
Advanced flags (run Python directly): see scripts/mcp/docs/MCP_AI_ENHANCEMENT.md.
Pipeline Overview
templates/index.json
│
▼ npm run mcp (sync_index.py)
templates/index.mcp.json ◄── merge description/io from template_cache (hash match)
│
├── npm run mcp:models → scripts/data/mcp/models_registry.json
└── npm run mcp:ai → scripts/data/mcp/template_cache.json → merge back to index.mcp.json
| Step | Script | Writes |
|---|---|---|
| 1 Sync | scripts/mcp/sync_index.py |
index.mcp.json, refreshes api_node_model_options.json |
| 2a Models | scripts/mcp/enhance_models_registry.py |
models_registry.json |
| 2b Templates | scripts/mcp/enhance_descriptions.py |
template_cache.json + merge → index.mcp.json |
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.
- yesterday Changed 113013cabbc9
- 10d ago First seen · 171 lines · 172 tokens per session scan A 185bd2e85bc0
managing-mcp-index is a skill published in the GitHub repository Comfy-Org/workflow_templates (884 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 1,971 once invoked, about $0.0009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…