mcp-base: Instructions file for Claude Code

CLAUDE.md

mcp-base CLAUDE.md is an instructions file for Claude Code from yone-k/mcp-base. It costs 1,737 tokens per session, scanned A, original, MIT.

A TypeScript starter project for building an MCP server, a service that lets compatible AI clients use defined tools.

In plain words
What is it for?
Use it to create MCP tools with a registry, shared validation and error handling, TypeScript types, Vitest tests, and a Node.js entry point.
Why use it?
It gives developers an organised starting structure instead of creating the server architecture from scratch.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is yone-k/mcp-base's own configuration. It tells Claude Code how to work on mcp-base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-base configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { ToolDefinition } from '../../types/mcp.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to yone-k/mcp-base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yone-k/mcp-base/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yone-k/mcp-base

Made for: Claude Code.

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-base CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yone-k/mcp-base/claude-md/github.svg)](https://agentmods.dev/instructions/yone-k/mcp-base/claude-md)
Your own site
<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/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.

agentmods 80×15 button for mcp-base CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,737 This file is loaded in full into every session.
When invoked 1,737 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01737 $0.01737
Opus 5.5 $0.00695 $0.00695
Sonnet 5.5 $0.00347 $0.00347
Haiku 4.5 $0.00174 $0.00174

Measured 2mo ago against content hash b2694397419f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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 · 215 lines

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

  1. 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
  2. ツールファイルの作成: src/tools/{category}/{tool-name}.ts
  3. 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
  4. レジストリへの登録: src/tools/registry.tsに追加
  5. ハンドラーの更新: src/core/tool-handler.tsのswitchケースに追加
  6. 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

Read the full file on GitHub · 215 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. 2mo ago First seen · 215 lines · 1,737 tokens per session scan A b2694397419f

Subscribe to this mod's changes

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 $0.0069 per session on Opus 5.5. 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

mcp-base CLAUDE.md compared with instructions from other repositories

mcp-base CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-base CLAUDE.mdyone-k/mcp-baseInstructions file01y agoMITA1,737Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot