What is commerce-mcp CLAUDE.md?

A set of instructions for AI agents working on commerce-mcp, a project that provides read-only tools for inspecting SAP Commerce Cloud, an online-commerce platform. It explains the project’s structure, technology choices, safety rules, and common commands.

It is for writing, reviewing, testing, and navigating this Node.js and TypeScript project, including its mock connector and MCP tool catalogue.

It gives an agent the project context and boundaries needed to work consistently, including the rule that the current tools are read-only and the live Hybris connection is not implemented.

How AlexTsvetkov/commerce-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AlexTsvetkov/commerce-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/AlexTsvetkov/commerce-mcp/main/CLAUDE.md

Clone the repo

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

Your own site

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

Per session 658 This file is loaded in full into every session.

When invoked 658 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	$0.00658	$0.00658
Opus 5	$0.00329	$0.00329
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 7d ago against content hash 15cd95326ad6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

commerce-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 7d 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and other AI agents) working in this repository.

What this project is

commerce-mcp — an AI/MCP control plane for SAP Commerce Cloud (Hybris). It exposes the estate (type system, FlexibleSearch, ImpEx, and — planned — business processes, feature toggles, order traces) to LLM agents as safe, typed, read-only tools over the Model Context Protocol.

Status: early scaffold. The tool catalogue, safety model and offline MockConnector are real and tested. The live Hybris connector (HAC/OCC/read-only DB) is a documented extension point, not yet implemented. Don't claim it exists.

Stack

Node 20 + TypeScript (strict), @modelcontextprotocol/sdk, zod, Vitest.

Project layout

src/types.ts — domain contracts + the CommerceConnector interface (the seam between mock and live).
src/mock-connector.ts — fixture-backed connector; assertReadOnly enforces SELECT-only.
src/tools/index.ts — the read-only MCP tool catalogue (zod-typed).
src/server/index.ts — MCP stdio server entrypoint.
test/ — Vitest.
docs/ — GitHub Pages site. Served at https://alextsvetkov.github.io/commerce-mcp/.

Common commands

npm install
npm run build      # tsc
npm start          # run MCP server on stdio (MockConnector)
npm run dev        # tsx, no build step
npm test           # vitest
npm run typecheck

Non-negotiable conventions

Read-only stays read-only. Every tool in the default catalogue must be non-mutating. run_flexible_search rejects non-SELECT statements via assertReadOnly. Write-capable tooling belongs behind a separate, explicitly-authorized surface — do not add mutating tools to the default catalogue.
The CommerceConnector interface is the contract. MockConnector and any future LiveConnector must stay interchangeable — never leak mock-only behaviour into tool logic.
Every tool needs a test using MockConnector (no live instance in CI).
Strict TypeScript; ESM with .js extensions in relative imports (NodeNext).
Conventional commits.

Read the full file on GitHub · 49 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.

7d ago First seen · 49 lines · 658 tokens per session scan A 15cd95326ad6

Subscribe to this mod's changes

commerce-mcp CLAUDE.md is an instructions file published in the GitHub repository AlexTsvetkov/commerce-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 658 tokens to every session, about $0.0033 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.

E-commerce

vibetags com-example-service-OrderService.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.

PIsberg/vibetags · 553 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

commerce-mcp: Instructions file for Claude Code