Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/nuxt-modules/mcp-toolkit/agents-mdgit clone --depth 1 https://github.com/nuxt-modules/mcp-toolkitWhat 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 | $0.07667 | $0.07667 |
| Opus 5 | $0.03834 | $0.03834 |
| Sonnet 5 | $0.01533 | $0.01533 |
| Haiku 4.5 | $0.00767 | $0.00767 |
Grade A, and why
mcp-toolkit AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A guide for AI coding agents working on the Nuxt MCP Toolkit project.
Project Overview
Nuxt MCP Toolkit is a Nuxt module that enables developers to create Model Context Protocol (MCP) servers directly in their Nuxt applications. It provides automatic discovery of tools, resources, and prompts with zero configuration - just create files and they're automatically registered.
Monorepo Structure
This is a pnpm monorepo managed with Turborepo:
nuxt-mcp-toolkit/
├── packages/
│ └── nuxt-mcp-toolkit/ # Main module (published as @nuxtjs/mcp-toolkit)
├── apps/
│ ├── docs/ # Documentation site (mcp-toolkit.nuxt.dev)
│ ├── playground/ # Development playground for testing
│ ├── mcp-starter/ # Minimal MCP template (`pnpm dev:starter`)
│ └── nitro-playground/ # Bare Nitro v3 app for nitro-mcp-toolkit (`pnpm dev:nitro`)
Development Environment Setup
Prerequisites
- Node.js 18+
- pnpm 9.15.0+
Initial Setup
# Install dependencies
pnpm install
# Generate type stubs (required before first run)
pnpm run dev:prepare
# Start the playground
pnpm run dev
# Start the docs site
pnpm run dev:docs
# Start the minimal MCP starter
pnpm run dev:starter
Common Commands
Run from the repository root:
| Command | Description |
|---|---|
pnpm dev |
Start the playground app |
pnpm dev:nitro |
Start the Nitro playground and its inspector UI on port 3030 |
pnpm probe:nitro |
Drive the Nitro playground with a real MCP client, from the CLI |
pnpm dev:starter |
Start the minimal MCP starter app |
pnpm dev:docs |
Start the documentation site |
pnpm build |
Build all packages |
pnpm build:module |
Build only the module |
pnpm build:nitro |
Build only the Nitro toolkit |
pnpm build:docs |
Build only the docs |
pnpm test |
Run all tests |
pnpm lint |
Run ESLint |
pnpm lint:fix |
Fix ESLint issues |
pnpm typecheck |
Run TypeScript type checking |
pnpm eval |
Run MCP evals (docs) |
pnpm eval:ui |
Run MCP evals with UI (docs) |
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.
- 2d ago First seen · 474 lines · 7,667 tokens per session scan A 964ad38ef162
mcp-toolkit AGENTS.md is an instructions file published in the GitHub repository nuxt-modules/mcp-toolkit (169 stars, last pushed 7d ago), licensed MIT. It adds 7,667 tokens to every session, about $0.0383 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 instructions, from other repositories
ui AGENTS.md
AGENTS.md instructions for nuxt/ui, covering agents.md, project overview, project structure, commands and cli for scaffolding.
ui CLAUDE.md
Claude Code instructions for nuxt/ui, a project described as: The Intuitive Vue UI Library powered by Reka UI & Tailwind CSS.
servicenow-platform-mcp AGENTS.md
Instructions for Xerrion/servicenow-platform-mcp, covering agents.md - servicenow-platform-mcp, 📋 project overview, dependencies, 🚀 setup and 🔧 lint / format / type-check.
css-noop-checker CLAUDE.md
Instructions for purupurupu/css-noop-checker, covering claude.md, project overview, commands, tech stack and architecture.
css-noop-checker AGENTS.md
Instructions for purupurupu/css-noop-checker, covering ai agent instructions, project structure, adding a new rule, 1. create the rule file and 2. register in engine.ts.
silentfail CLAUDE.md
Claude Code instructions for decksaga/silentfail, covering silentfail, commands, stack, modes and key files.