What is webcake-storefront-mcp CLAUDE.md?

Project instructions for WebCake Storefront MCP, a server that lets AI coding tools access WebCake and StoreCake content-management features.

Use them when installing, building, running, developing, or configuring this TypeScript server for Claude, Cursor, Windsurf, VS Code, or another supported AI tool.

They give contributors the repository's setup commands, required build step, login process, server modes, and project structure in one place.

How vuluu2k/webcake-storefront-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vuluu2k/webcake-storefront-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/vuluu2k/webcake-storefront-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vuluu2k/webcake-storefront-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/vuluu2k/webcake-storefront-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vuluu2k/webcake-storefront-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vuluu2k/webcake-storefront-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vuluu2k/webcake-storefront-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/vuluu2k/webcake-storefront-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vuluu2k/webcake-storefront-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,510 This file is loaded in full into every session.

When invoked 2,510 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	$0.02510	$0.02510
Opus 5.5	$0.01004	$0.01004
Sonnet 5.5	$0.00502	$0.00502
Haiku 4.5	$0.00251	$0.00251

Measured 8d ago against content hash d55e5fb7186a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webcake-storefront-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 8d 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 · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 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.

What This Is

An MCP (Model Context Protocol) server that exposes WebCake CMS features as tools for AI agents. It acts as a bridge between AI IDEs (Claude Desktop, Claude Code, Cursor, Windsurf, Augment) and the WebCake/StoreCake CMS backend API.

Commands

npm install          # Install dependencies
npm run build        # Compile TypeScript (src/ → dist/) + copy assets. REQUIRED before running.
npm start            # Run the built stdio MCP server (node dist/index.js)
npm run serve        # Run the remote Streamable-HTTP server (node dist/index.js serve)
npm run dev          # tsc --watch

# CLI subcommands (also available via `npx -y webcake-storefront-mcp <cmd>`):
node dist/index.js              # stdio MCP server (default; use in IDE configs)
node dist/index.js install      # no questions: prod, browser Connect, every detected IDE (--dev: wizard with env choice)
node dist/index.js login        # browser login → saves token to ~/.webcake-storefront-mcp/ db
node dist/index.js serve --port 8787   # remote Streamable-HTTP MCP

This is a TypeScript project (strict). All source lives in src/ and compiles to dist/; the published bin is dist/index.js. The server runs over stdio by default (for IDE configs) and can also run as a remote Streamable-HTTP server via serve. Config (token/site/api_url) is read from env vars or a SQLite db at ~/.webcake-storefront-mcp/ (survives npx).

Environment Variables

Required (auth):

WEBCAKE_TOKEN — storefront JWT Bearer token (the builder's jwt cookie / store_jwt)
WEBCAKE_SESSION_ID — session id, sent as the x-session-id header (the builder's wsid cookie)

The site is not set from env — it's chosen at runtime via the list_my_sites + switch_site tools (persisted to the local db, restored next session). WEBCAKE_SITE_ID still works as an optional override if you want to pin a site, and remote mode can pass x-webcake-site-id / ?site_id= per request.

Read the full file on GitHub · 112 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.

8d ago Changed · +1 lines · +37 tokens per session d55e5fb7186a
9d ago Changed · +1 lines · +168 tokens per session 6440c354ca8e
2mo ago First seen · 110 lines · 2,305 tokens per session scan A 3361b2f3309a

Subscribe to this mod's changes

webcake-storefront-mcp CLAUDE.md is an instructions file published in the GitHub repository vuluu2k/webcake-storefront-mcp (4 stars, last pushed today), licensed MIT. It adds 2,510 tokens to every session, about $0.0100 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

webcake-storefront-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
webcake-storefront-mcp CLAUDE.mdvuluu2k/webcake-storefront-mcp	Instructions file	4	today	MIT	A	2,510	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	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

webcake-storefront-mcp: Instructions file for Claude Code