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/yone-k/mcp-base/claude-mdgit clone --depth 1 https://github.com/yone-k/mcp-baseWrote 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/yone-k/mcp-base/claude-md)<a href="https://agentmods.dev/instructions/yone-k/mcp-base/claude-md"><img src="https://agentmods.dev/badge/instructions/yone-k/mcp-base/claude-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 | $0.01737 | $0.01737 |
| Opus 5 | $0.00869 | $0.00869 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
mcp-base 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 5d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Base Server
プロジェクト概要
汎用的なMCP (Model Context Protocol) サーバーのベーステンプレートです。新しいMCPサーバーを簡単に作成できるように設計されています。
技術スタック
- 言語: TypeScript
- フレームワーク: MCP SDK (@modelcontextprotocol/sdk)
- バリデーション: Zod
- 実行環境: Node.js 22+
- テストフレームワーク: Vitest
アーキテクチャ
設計方針
MCPプロトコル準拠: Model Context Protocolの仕様に完全準拠し、標準的なMCPクライアントとの互換性を保つ モジュラー設計: ツール実装を独立したモジュールとして管理し、拡張性を重視 型安全性: TypeScriptとZodを活用した厳密な型チェック テンプレート性: 新しいMCPサーバー開発の出発点として使用可能
ディレクトリ構造
mcp-base/
├── src/
│ ├── core/ # MCPサーバーのコア機能
│ │ └── tool-handler.ts # 共通ツールハンドラー
│ ├── tools/ # MCPツール実装(カテゴリ別整理)
│ │ ├── registry.ts # ツールレジストリ
│ │ └── example/ # サンプルツール実装
│ ├── types/ # 型定義
│ └── index.ts # エントリーポイント
├── package.json # 依存関係とスクリプト
├── tsconfig.json # TypeScript設定
├── vitest.config.ts # テスト設定
├── README.md # 使用方法
└── CLAUDE.md # このファイル
ツール管理アーキテクチャ
ツールレジストリパターン: 各ツールファイルにMCP定義を含め、registry.tsで一元管理
動的ツール登録: index.tsはレジストリから動的にツール一覧を取得
共通ハンドラー: ToolHandlerクラスがバリデーションとエラーハンドリングを統一
開発ガイドライン
コーディング規約
- ファイル命名: kebab-case (例: example-tool.ts)
- クラス命名: PascalCase (例: BaseMCPServer)
- 関数・変数命名: camelCase (例: setupHandlers)
- 定数命名: UPPER_SNAKE_CASE (例: DEFAULT_TIMEOUT)
- 型命名: PascalCase with suffix (例: ExampleToolInput)
新規ツール追加フロー
- カテゴリの決定: 追加するツールが属するカテゴリを決定
- ツールファイルの作成:
src/tools/{category}/{tool-name}.ts - ツール定義の実装: 以下の要素を含める
- 入力スキーマ(Zod)
- 出力スキーマ(Zod)
- ツール定義(MCP形式)
- 実装関数
- レジストリへの登録:
src/tools/registry.tsに追加 - ハンドラーの更新:
src/core/tool-handler.tsのswitchケースに追加 - テストの作成:
src/tools/{category}/{tool-name}.test.ts
開発コマンド
# Docker環境での開発
npm run docker:build # Dockerイメージをビルド
npm run docker:run # Dockerコンテナを実行
npm run docker:dev # Docker Composeで開発環境を起動
# ローカル開発
npm run dev
# テスト実行
npm test
npm run test:watch # 監視モード
npm run test:coverage # カバレッジ付き
# ビルド
npm run build
# lint/typecheck
npm run lint
npm run typecheck
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.
- 5d ago First seen · 215 lines · 1,737 tokens per session scan A b2694397419f
mcp-base CLAUDE.md is an instructions file published in the GitHub repository yone-k/mcp-base (0 stars, last pushed 1y ago), licensed MIT. It adds 1,737 tokens to every session, about $0.0087 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.
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.
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).
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.
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.
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.
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).