What is mcp-server CLAUDE.md?

Project instructions for developing a PortOne MCP server in Node.js and TypeScript. They document commands, coding conventions, testing, formatting, and the main libraries used by the project.

Use them to install dependencies, run the server, build it, check types, lint, format, and run all or individual tests. They also guide TypeScript structure, naming, imports, errors, and documentation.

They give contributors a shared way to build, check, and maintain the server. This reduces uncertainty about which commands and standards to follow.

How portone-io/mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to portone-io/mcp-server. 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/portone-io/mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/portone-io/mcp-server

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/portone-io/mcp-server/claude-md.svg)](https://agentmods.dev/instructions/portone-io/mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/portone-io/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/portone-io/mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,020 This file is loaded in full into every session.

When invoked 1,020 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01020	$0.01020
Opus 5	$0.00510	$0.00510
Sonnet 5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 6d ago against content hash acc51d2d8b92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

mcp-server CLAUDE.md scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. Clean build directory: `rm -rf dist`

CLAUDE.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

PortOne MCP Server Development Guidelines

Build & Test Commands

Setup: pnpm install
Run server: pnpm dev
Run all tests: pnpm test
Run single test: pnpm test tests/loader.test.ts
Lint code: pnpm lint
Format code: pnpm format
Build: pnpm build
Type check: pnpm typecheck

Code Style Guidelines

Node.js 22+ and TypeScript 5+ required
Use type annotations for all function parameters and return values
Follow TypeScript/JavaScript conventions
Use interfaces and types for data structures
Organize imports: Node.js built-ins first, then third-party, then local
Error handling: use descriptive error messages
Naming: camelCase for functions/variables, PascalCase for classes/interfaces
Documentation: document classes and functions with JSDoc comments
Tests: write unit tests using Vitest for critical functions
Code formatting and linting excludes: dist/, assets/, and server/ directories

Dependencies

Key dependencies include:

@modelcontextprotocol/sdk: MCP server framework
@portone/server-sdk: PortOne SDK for server-side operations
graphql & graphql-request: GraphQL client for API communication
h3: HTTP server for OAuth callback handling
open: Cross-platform library for opening URLs in browser
gray-matter: YAML frontmatter parsing
js-yaml: YAML processing
zod: Schema validation
ts-pattern: Pattern matching for TypeScript

Architecture Overview

This is an MCP (Model Context Protocol) server that provides AI tools for accessing PortOne documentation. Key components:

Resource Loading System

loader/ module handles document parsing and resource loading
Markdown documents are parsed with YAML frontmatter support
Schema files (OpenAPI, GraphQL) are loaded from the assets/docs/schema/ directory
All resources are loaded at server startup via load_resources()

Read the full file on GitHub · 103 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.

6d ago First seen · 103 lines · 1,020 tokens per session scan C acc51d2d8b92

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository portone-io/mcp-server (27 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,020 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 5,182 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-server: Instructions file for Claude Code