What is AppStoresMCP CLAUDE.md?

A contributor guide for AppStoresMCP, a Node.js and TypeScript MCP server that collects information from app stores. MCP is a standard way for an AI agent to use external tools.

Use it when building, testing, linting, running, or containerising AppStoresMCP, including its app-store scraping tools.

It puts build, test, development, Docker, and architecture instructions in one place for contributors and coding agents.

How guiguito/AppStoresMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to guiguito/AppStoresMCP. 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/guiguito/AppStoresMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/guiguito/AppStoresMCP

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/guiguito/appstoresmcp/claude-md/github.svg)](https://agentmods.dev/instructions/guiguito/appstoresmcp/claude-md)

Your own site

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

Per session 1,209 This file is loaded in full into every session.

When invoked 1,209 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	$0.01209	$0.01209
Opus 5.5	$0.00484	$0.00484
Sonnet 5.5	$0.00242	$0.00242
Haiku 4.5	$0.00121	$0.00121

Measured 6d ago against content hash 4c62358bc0a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AppStoresMCP 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 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.

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 · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 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.

Development Commands

Building and Testing

npm run build - Build TypeScript to JavaScript
npm run test - Run all tests (unit and integration)
npm run test:unit - Run unit tests only
npm run test:integration - Run integration tests (scrapers mocked)
npm run test:live - Build and call all 20 tools against the real stores (catches store/library drift; unit tests mock the scrapers)
npm run test:coverage - Run tests with coverage report
npm run lint - Run ESLint on src, scripts, tools and examples

CI (.github/workflows/ci.yml) runs lint, build and tests on Node 20/22/24 for pushes and PRs to main. .github/workflows/live.yml runs npm run test:live every Monday and on demand.

Development

npm run dev - Start development server with ts-node
npm start - Start production server from dist/

Docker Commands

docker-compose up --build - Build and run with Docker Compose
npm run test:integration:docker - Build the Docker image and run the live check inside it
./scripts/generate-ssl-certs.sh - Generate SSL certificates for HTTPS

Architecture Overview

This is a Node.js TypeScript MCP (Model Context Protocol) server that provides app store scraping functionality through multiple transport protocols.

Core Components

MCPServer (src/server.ts) - Main orchestrator that manages:

HTTP and SSE transport handlers
Tool registry with 20 MCP tools
Configuration management
Graceful shutdown handling

Transport Layer (src/transport/)

HTTPTransportHandler - MCP Streamable HTTP protocol implementation
SSETransportHandler - Standard MCP HTTP+SSE transport (2024-11-05): endpoint event, 202 on POST, responses as message events

Protocol Handler (src/protocol/mcp-handler.ts)

Processes MCP messages (initialize, tools/list, tools/call)
Tool failures (validation or library errors) are returned as isError: true results; no server-side retries (the scraper libraries retry 429/5xx themselves)
Returns raw data from underlying scraper libraries

Read the full file on GitHub · 111 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 Changed · -2 lines · +275 tokens per session 4c62358bc0a6
2mo ago First seen · 113 lines · 934 tokens per session scan A 2b0fed7527df

Subscribe to this mod's changes

AppStoresMCP CLAUDE.md is an instructions file published in the GitHub repository guiguito/AppStoresMCP (5 stars, last pushed 6d ago), licensed MIT. It adds 1,209 tokens to every session, about $0.0048 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.

AppStoresMCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AppStoresMCP CLAUDE.mdguiguito/AppStoresMCP	Instructions file	5	6d ago	MIT	A	1,209	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
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
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

AppStoresMCP: Instructions file for Claude Code