mcp-toolkit CLAUDE.md

mcp-toolkit CLAUDE.md is an instructions file for coding agents from us-all/mcp-toolkit. It costs 3,620 tokens per session, scanned A, original, MIT.

Repository instructions for mcp-toolkit, a TypeScript package of shared building blocks for MCP servers. MCP servers are programs that expose tools and data to AI clients; the instructions cover the project's structure, build commands, and design principles.

In plain words
What is it for?
Use them when developing, building, or testing the package's field extraction, tool registry, error handling, aggregation, and server runtime code.
Why use it?
They give coding agents the project's purpose, supported technology versions, directory layout, and testing context before they make changes.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/us-all/mcp-toolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/us-all/mcp-toolkit

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 mcp-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/us-all/mcp-toolkit/claude-md.svg)](https://agentmods.dev/instructions/us-all/mcp-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/us-all/mcp-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/us-all/mcp-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,620 This file is loaded in full into every session.
When invoked 3,620 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03620 $0.03620
Opus 5 $0.01810 $0.01810
Sonnet 5 $0.00724 $0.00724
Haiku 4.5 $0.00362 $0.00362

Measured 3d ago against content hash 43c44962f149, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-toolkit 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 3d 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

이 파일은 Claude Code가 이 저장소에서 작업할 때 참고하는 컨텍스트입니다.

프로젝트 개요

@us-all/mcp-toolkit@us-all/* MCP 서버용 공통 빌딩 블록. 6개 production MCP에서 검증된 토큰 효율 패턴을 단일 npm 패키지로 추출.

  • 타겟: Node 18+, ESM, TypeScript strict
  • Peer deps: @modelcontextprotocol/sdk ^1.27 || ^1.28 || ^1.29, zod ^4
  • 목적: 6 production MCP의 코드 중복 제거 + 패턴 진화 시 단일 진실 소스
  • 표준 문서: STANDARD.md — 패턴의 why, 이 패키지는 how

디렉토리

src/
├── extract-fields.ts       # applyExtractFields(data, expr?) — 응답 필드 프로젝션
├── registry.ts             # ToolRegistry<TCategory> + createSearchToolsMetaTool + parseEnvList
├── wrap-tool-handler.ts    # createWrapToolHandler — 에러 sanitize + structured 응답 + extractFields auto-apply
├── aggregate.ts            # aggregate(fetchers, caveats) — Promise.allSettled + 라벨링된 caveats 보일러플레이트 통합
├── runtime.ts              # startMcpServer(server, opts?) — stdio + Streamable HTTP (node:http + Bearer auth)
└── index.ts                # re-export 통합 진입점
tests/
├── extract-fields.test.ts      # 9 cases — wildcards, backtick keys, projection 엣지
├── registry.test.ts            # 11 cases — search 매칭, 카테고리 토글, allowlist/denylist
├── wrap-tool-handler.test.ts   # 16 cases — 성공/에러 경로, 커스텀 redaction, errorExtractors
├── aggregate.test.ts           # 11 cases — 성공/거부 mix, 커스텀 formatReason, 동시성 검증
└── runtime.test.ts             # 7 cases — 환경변수/옵션 해석, Bearer 인증, /health, skipAuth
STANDARD.md             # us-all MCP 작성 표준 (패턴 가이드)

Build & Run

pnpm install
pnpm build          # tsc → dist/
pnpm test           # 36 unit tests

설계 원칙

  • Pure functions / pure classes: 외부 의존성 없는 도메인-독립 코드만 추출. SDK/auth 등 도메인 특수 로직은 각 repo에 유지.
  • Generic categories: ToolRegistry<TCategory> — 각 repo가 자체 CATEGORIES 상수를 typed로 정의해서 사용.
  • Always-enabled meta: meta 카테고리는 기본적으로 항상 활성. alwaysEnabled 옵션으로 커스터마이즈 가능.
  • Schema opt-in: extractFields는 각 도구 schema가 명시적으로 선언해야 동작 (MCP SDK가 미선언 필드를 validation에서 drop). STANDARD.md에 caveat 명시.

Read the full file on GitHub · 152 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. 3d ago First seen · 152 lines · 3,620 tokens per session scan A 43c44962f149

Subscribe to this mod's changes

mcp-toolkit CLAUDE.md is an instructions file published in the GitHub repository us-all/mcp-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 3,620 tokens to every session, about $0.0181 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

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

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

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 · 4,345 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

next.js 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