Borrowing it
Nothing to install: this file belongs to Fourni-j/appstore-connect-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.
curl -O https://raw.githubusercontent.com/Fourni-j/appstore-connect-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/Fourni-j/appstore-connect-MCPWrote 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.
[](https://agentmods.dev/instructions/fourni-j/appstore-connect-mcp/claude-md)<a href="https://agentmods.dev/instructions/fourni-j/appstore-connect-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fourni-j/appstore-connect-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.
<a href="https://agentmods.dev/instructions/fourni-j/appstore-connect-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fourni-j/appstore-connect-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02055 | $0.02055 |
| Opus 5 | $0.01027 | $0.01027 |
| Sonnet 5 | $0.00411 | $0.00411 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
appstore-connect-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store Connect MCP Server
Open Source Project — IMPORTANT
This is a public open-source repository. Every change you make may be seen by anyone. Follow these rules strictly:
Never leak secrets
- NEVER hardcode, log, or commit API keys, key IDs, issuer IDs, vendor numbers, private key paths, or any credential.
- NEVER include real app IDs, bundle IDs, or user-specific data in code, tests, comments, or documentation. Use placeholder values (e.g.,
"your-key-id","123","com.example.myapp"). - If a tool call result or conversation context contains real credentials or user data, do not copy it into any file.
Keep documentation up to date
When adding, modifying, or removing a tool or feature:
- README.md — Update the Tools section (parameters, description), response examples, test count, and local testing commands.
- CLAUDE.md — Update the Architecture tree, Key Patterns, and Agent-Friendly Response Format sections.
- Tool description in
index.ts— Keep theserver.tool()description accurate and complete for agent consumption. scripts/test-tools.ts— Add an integration test block for any new tool.
Tests are mandatory
- Every new tool handler must have a corresponding test file in
src/__tests__/. - All tests must pass (
npm test) before considering work complete. - Keep the test count in README.md accurate.
Build & Test
npm run build # TypeScript compilation
npm test # Run all tests (vitest)
npm run test:watch # Watch mode
npx tsx scripts/test-tools.ts # Run all tools against the real API
npx tsx scripts/test-tools.ts list-apps # Run a single tool
Architecture
src/
index.ts # MCP server entry point, tool registration and descriptions
auth.ts # JWT generation + caching for App Store Connect API
api/
client.ts # HTTP client with retry logic (429/5xx backoff) + fetchUrl for pre-signed S3 URLs
apps.ts # Apps, metadata, and versions API calls (with in-memory app list cache)
sales-reports.ts # Sales reports (gzip download + TSV parsing)
analytics.ts # Analytics reports (async report request/instance/segment flow, with segment cache)
reviews.ts # Customer reviews (paginated) + App Store rating via iTunes Lookup API
tools/
list-apps.ts # List apps — returns id, name, bundleId, SKU
get-app-metadata.ts # Localized metadata — name, subtitle, keywords, description, promotionalText
get-sales-report.ts # Sales/installs reports — column mapping, product type labels, truncation
get-analytics-report.ts # Analytics — aggregated or raw mode, engagement enriched with COMMERCE data
get-app-store-versions.ts # App versions with App Store state
get-downloads-summary.ts # Download trends — daily/monthly auto-selection from sales reports
get-customer-reviews.ts # Customer reviews — written reviews + App Store rating, date/rating/territory filtering
utils/
tsv.ts # TSV parser (first row = headers)
compression.ts # Gzip decompression via node:zlib
__tests__/ # Unit tests (vitest)
scripts/
test-tools.ts # Manual integration test — calls handlers against the real API
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.
- 9d ago First seen · 137 lines · 2,055 tokens per session scan A c521dfdafbe2
appstore-connect-MCP CLAUDE.md is an instructions file published in the GitHub repository Fourni-j/appstore-connect-MCP (1 stars, last pushed 6mo ago), licensed MIT. It adds 2,055 tokens to every session, about $0.0103 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.