What is mcp-server CLAUDE.md?

Repository instructions for working on Passgage API MCP, a TypeScript and Node.js server that lets AI assistants use Passgage's workforce-management API. They describe the project structure, development commands, and code-quality checks.

They are for developing and validating the Passgage MCP server, including its API client, authentication, types, tests, and production build.

They give an agent the project's expected workflow and the commands used to build, test, lint, and type-check changes. This reduces guesswork when modifying the repository.

How passgage/mcp-server configures Claude Code

Reuse

Borrowing it

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

Clone the repo

git clone --depth 1 https://github.com/passgage/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/passgage/mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/passgage/mcp-server/claude-md)

Your own site

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

Per session 1,389 This file is loaded in full into every session.

When invoked 1,389 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	$0.01389	$0.01389
Opus 5.5	$0.00556	$0.00556
Sonnet 5.5	$0.00278	$0.00278
Haiku 4.5	$0.00139	$0.00139

Measured 2mo ago against content hash c1bccf48d982, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 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.

Project Overview

This is a comprehensive Passgage API MCP (Model Context Protocol) Server built with TypeScript and Node.js. The server provides 130+ tools to interact with the complete Passgage Public API surface area, enabling AI assistants like Claude to manage workforce operations, approvals, time tracking, and more.

Development Commands

Build and Run

npm run build - Compile TypeScript to JavaScript
npm run dev - Development mode with hot reload using tsx
npm start - Start production server from dist/
npm run type-check - TypeScript type checking without compilation

Code Quality

npm run lint - Run ESLint on TypeScript files in src/ directory
npm run lint:fix - Auto-fix linting issues
npm test - Run Jest tests with NODE_OPTIONS='--experimental-vm-modules'
npm run type-check - TypeScript type checking (recommended before commits)

Project Architecture

Core Components

src/api/client.ts - Passgage API client with JWT auth, auto-refresh, error handling
src/types/api.ts - Complete TypeScript definitions for Passgage API
src/config/index.ts - Environment configuration and validation
src/index.ts - MCP server implementation with stdio transport

Tool Categories

src/tools/auth.ts - Authentication tools (login, logout, refresh, status)
src/tools/crud.ts - CRUD operations for 25+ Passgage services (125 tools)
src/tools/specialized.ts - Advanced tools (file upload, approvals, search, export)

MCP Tools Structure

The server provides 133 total tools:

8 Authentication tools - JWT session and mode management
125 CRUD tools - 5 operations × 25 services (list, get, create, update, delete)
8 Specialized tools - File upload, bulk approvals, search, dashboard stats

Configuration

Environment Variables (.env)

# Required: Choose one authentication method
PASSGAGE_API_KEY=company_api_key          # OR
[email protected]      
PASSGAGE_USER_PASSWORD=password

# API Configuration
PASSGAGE_BASE_URL=https://api.passgage.com
PASSGAGE_TIMEOUT=30000
PASSGAGE_DEBUG=false

Read the full file on GitHub · 153 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.

2mo ago First seen · 153 lines · 1,389 tokens per session scan A c1bccf48d982

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository passgage/mcp-server (1 stars, last pushed 1y ago), licensed MIT. It adds 1,389 tokens to every session, about $0.0056 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.

Backend and APIs ai employee-management hr mcp mcp-server passgage

mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server CLAUDE.mdpassgage/mcp-server	Instructions file	1	1y ago	MIT	A	1,389	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-server: Instructions file for Claude Code