What is mcp-boilerplate CLAUDE.md?

A set of Claude Code instructions for a TypeScript template used to build MCP servers. MCP servers provide an AI assistant with tools, information, or reusable prompts through local or remote connections.

Use it when extending or maintaining this MCP server boilerplate, including its local stdio connection or remote HTTP connection.

It gives contributors shared rules for code layout, input checking, errors, logging, and the checks required before a change is complete.

How SekiroKenjii/mcp-boilerplate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SekiroKenjii/mcp-boilerplate. 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/SekiroKenjii/mcp-boilerplate/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SekiroKenjii/mcp-boilerplate

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sekirokenjii/mcp-boilerplate/claude-md/github.svg)](https://agentmods.dev/instructions/sekirokenjii/mcp-boilerplate/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sekirokenjii/mcp-boilerplate/claude-md"><img src="https://agentmods.dev/badge/instructions/sekirokenjii/mcp-boilerplate/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sekirokenjii/mcp-boilerplate/claude-md"><img src="https://agentmods.dev/badge/instructions/sekirokenjii/mcp-boilerplate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 815 This file is loaded in full into every session.

When invoked 815 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.

Model	Per session	Once invoked
Fable 5.1	$0.00815	$0.00815
Opus 5	$0.00407	$0.00407
Sonnet 5	$0.00163	$0.00163
Haiku 4.5	$0.00081	$0.00081

Measured 10d ago against content hash 55673cb4405a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-boilerplate 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 10d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and humans) working in this repository.

What this is

A production-grade boilerplate for building MCP (Model Context Protocol) servers in TypeScript. It exposes tools, resources, and prompts over two transports: stdio (local clients) and Streamable HTTP (remote/hosted). SDK: @modelcontextprotocol/sdk (1.x).

Golden rules

Logs go to stderr only. stdout is the stdio JSON-RPC channel. Use logger from src/core/logger.ts; never console.log.
Surface assumptions, keep changes surgical, prefer the simplest solution. See the karpathy-guidelines skill — it applies to all work here.
Validate all external input through Zod schemas. Tool handlers must not throw raw; return toToolError(error) from src/core/errors.ts.
Every change must pass pnpm typecheck && pnpm lint && pnpm test before it's done.
Use the context7 MCP to confirm current API syntax for the SDK, Zod, Express, etc. before relying on memory — these libraries move quickly.

Layout

src/
  index.ts          Entrypoint: resolves transport (--transport / MCP_TRANSPORT), graceful shutdown
  server.ts         createServer(): builds McpServer and registers features
  config/env.ts     Zod-validated environment configuration
  core/             logger (stderr), errors (AppError + toToolError), pkg, auth (optional bearer)
  transports/       stdio.ts and http.ts (Express + Streamable HTTP, sessions, /healthz)
  tools/            One file per tool + index.ts aggregator (example: echo.tool.ts)
  resources/        One file per resource + index.ts aggregator
  prompts/          One file per prompt + index.ts aggregator
tests/              Vitest; connect an in-memory Client to the real server via helpers/connect.ts

Adding a feature = new file in the relevant folder + one import line in that folder's index.ts.

How to extend

Add a tool → use the mcp-add-tool skill (or /new-tool).
Add a resource → mcp-add-resource skill (or /new-resource).
Add a prompt → mcp-add-prompt skill (or /new-prompt).

Read the full file on GitHub · 66 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.

10d ago First seen · 66 lines · 815 tokens per session scan A 55673cb4405a

Subscribe to this mod's changes

mcp-boilerplate CLAUDE.md is an instructions file published in the GitHub repository SekiroKenjii/mcp-boilerplate (0 stars, last pushed 2mo ago), licensed MIT. It adds 815 tokens to every session, about $0.0041 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.

Building agents

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.

vercel/next.js · 7,296 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 · 5,153 tokens

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

mcp-boilerplate: Instructions file for Claude Code