Borrowing it
Nothing to install: this file belongs to erayendes/app-store-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/erayendes/app-store-connect-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/erayendes/app-store-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/erayendes/app-store-connect-mcp/agents-md)<a href="https://agentmods.dev/instructions/erayendes/app-store-connect-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/erayendes/app-store-connect-mcp/agents-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/erayendes/app-store-connect-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/erayendes/app-store-connect-mcp/agents-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 | $0.01706 | $0.01706 |
| Opus 5.5 | $0.00682 | $0.00682 |
| Sonnet 5.5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
app-store-connect-mcp AGENTS.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Going after the key is the most common way a session goes wrong.** In recorded eval runs, of the sessions that abandoned the tools, the largest group went hunting for the private key — `security find-generic-password`, How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (Claude Code, Codex, Cursor, Antigravity, and any other MCP client). Human-facing docs live in README.md and docs/.
The same guidance ships as a skill at
skills/heimdall/SKILL.md, whichregisterinstalls for the clients that read skills. That file exists because this one cannot be reached: Heimdall runs throughnpx, so a user installing it has no checkout and never sees AGENTS.md. Keep the two in step — if you change how install or safety works here, change it there too.
What this is
Heimdall is an MCP server for the App Store Connect API and the App Store Server API (StoreKit 2). It is published to npm as @erayendes/asc-mcp and runs via npx — there is nothing to clone, build, or npm install to use it. It is client-agnostic: standard MCP over stdio. It serves 929 tools across 13 profiles: 888 generated from Apple's 1011 operations (the 123 deprecated ones stay unloaded unless asked for) and 41 hand-written.
If a user asks you to install it
The install is two steps and they are not both yours. You register. The user hands over the key.
1. Agree on the profiles, then register them
Ask what the user works on. If they have not said, analytics, marketing and app-info are a sensible default. Each profile is a small scoped server; the table is in PROFILES_en.md.
A big profile takes a colon and a list of its sub-profiles — monetization:subscription-pricing,subscription-offers is 56 tools where monetization is 212. Worth suggesting for monetization, game-center, distribution, marketing and access. The server is still called ASC-Monetization.
Say what you are about to do and wait for a yes, then run:
npx -y @erayendes/asc-mcp register monetization:subscription-pricing analytics
This edits MCP client configs the user did not open — by default every client it finds, which is usually more than the one you are talking through. There is no confirmation prompt in the command, so the confirmation has to happen in the conversation. --clients=codex,claude limits it; --clients ids are claude, codex, antigravity, vscode, cursor, windsurf.
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.
- today Changed b7d1f0d2f692
- yesterday Changed 1b3fd4303d9f
- 8d ago Changed · +9 tokens per session 12c8942e629b
- 9d ago Changed · +1 lines · +128 tokens per session 2afd0695c9af
- 11d ago Changed · +1 lines · +83 tokens per session b4aec2fc9d4e
- 13d ago Changed · +31 tokens per session 728b94345276
- 15d ago Changed · -100 tokens per session c9b5b8a54a21
- 20d ago Changed · +159 tokens per session f947a1431a69
- 24d ago Changed 40bce96f872c
- 26d ago First seen · 59 lines · 1,396 tokens per session scan A 52cc64cfe688
app-store-connect-mcp AGENTS.md is an instructions file published in the GitHub repository erayendes/app-store-connect-mcp (53 stars, last pushed today), licensed MIT. It adds 1,706 tokens to every session, about $0.0068 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.