What is hw-mcp CLAUDE.md?

A project instruction file for Hertwill MCP, a server that lets AI agents search products and manage imports for a dropshipping business.

It guides development of the TypeScript MCP server, its Hertwill product-sourcing features, Shopify and WooCommerce syncing, npm distribution, and local standard-input/output transport.

It gives coding agents the project's goals, technical choices, authentication method, and limits so changes fit the existing system.

How Hertwill/hw-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Hertwill/hw-mcp. 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/Hertwill/hw-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Hertwill/hw-mcp

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/hertwill/hw-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hertwill/hw-mcp/claude-md)

Your own site

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

Per session 6,105 This file is loaded in full into every session.

When invoked 6,105 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	$0.06105	$0.06105
Opus 5.5	$0.02442	$0.02442
Sonnet 5.5	$0.01221	$0.01221
Haiku 4.5	$0.00611	$0.00611

Measured 2mo ago against content hash 56785ba83af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hw-mcp 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 · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

Hertwill MCP

A public Model Context Protocol (MCP) server that wraps the Hertwill dropshipping API, plus a bundled Claude Skill encoding the Hertwill sourcing playbook. It lets any MCP-capable AI agent (Claude Desktop, Cursor, Cline, Continue, Windsurf, Zed, VS Code + Copilot, Goose, OpenCode, Replit) discover Hertwill products, manage an import list, and trigger syncs to Shopify/WooCommerce — turning product sourcing for dropshippers from a multi-step manual workflow into a conversational one.

Core Value: Make sourcing Hertwill products as simple as a single natural-language request from any AI agent. Every scope decision should reduce the friction between "I need winning EU-shippable products under €30" and "they're in my Shopify import list."

Constraints

Tech stack: TypeScript + @modelcontextprotocol/sdk (official TS SDK) — biggest community, smallest install footprint, fastest ecosystem updates
Transport: stdio only for v1 — zero infra cost, no uptime burden on Hertwill
Distribution: npm (public) + GitHub (public repo) — required for directory listings
Auth model: env var (HERTWILL_API_KEY) for authenticated endpoints — matches stdio convention, no OAuth infra required
Rate limits: 60 req/min public, 300 req/min authenticated — client must throttle and return structured errors when limits hit
API compatibility: must stay in sync with Hertwill API changes — versioning strategy needed so the MCP can deprecate tools gracefully
Security: never log or persist API keys; never ship a default key in the package

Technology Stack

Executive Recommendation

@modelcontextprotocol/sdk@^1.29 with the high-level McpServer + registerTool API over StdioServerTransport
zod@^4.3 for tool input schemas, leveraging the SDK's built-in Zod-v4 → JSON Schema bridge (no zod-to-json-schema needed)
Native fetch (Node 20+ built-in, undici under the hood) wrapped in a thin client — no axios, no ky, no ofetch
openapi-typescript@^7.13 to generate types from Hertwill's OpenAPI 3.1 spec, consumed via openapi-fetch@^0.17 for a 6 KB fully-typed client
bottleneck@^2.19 for rate limiting (60/min public, 300/min authenticated) + p-retry@^6.2 for exponential backoff
pino@^10.3 piped to pino.destination(2) (stderr) — stdout is reserved for JSON-RPC
tsup@^8.5 for ESM-only build with shebang-injected bin entry
vitest@^4.1 for unit/integration tests, @modelcontextprotocol/inspector@^0.21 for interactive debugging
Claude Skill bundled as skills/hertwill-sourcing/SKILL.md in the same repo, distributed via the same npm package plus a separate "plugin" artifact for Claude Code users

Read the full file on GitHub · 207 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 · 207 lines · 6,105 tokens per session scan A 56785ba83af4

Subscribe to this mod's changes

hw-mcp CLAUDE.md is an instructions file published in the GitHub repository Hertwill/hw-mcp (5 stars, last pushed 4mo ago), licensed MIT. It adds 6,105 tokens to every session, about $0.0244 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.

E-commerce

hw-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hw-mcp CLAUDE.mdHertwill/hw-mcp	Instructions file	5	4mo ago	MIT	A	6,105	Claude Code
vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags	Instructions file	25	today	MIT	A	553	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot

hw-mcp: Instructions file for Claude Code