Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/vvlladd/appstoreconnectmcp/agents-mdgit clone --depth 1 https://github.com/Vvlladd/AppStoreConnectMCPWrote 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/vvlladd/appstoreconnectmcp/agents-md)<a href="https://agentmods.dev/instructions/vvlladd/appstoreconnectmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vvlladd/appstoreconnectmcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00591 | $0.00591 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
AppStoreConnectMCP AGENTS.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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store Connect MCP Server
Project Overview
A Swift MCP (Model Context Protocol) server that exposes App Store Connect REST API operations as tools for AI agents. Built as a macOS command-line tool using Tuist for project generation.
Tech Stack
- Language: Swift 6.0 (strict concurrency)
- Build system: Tuist 4.x (
Project.swift,Tuist/Package.swift) - Dependencies: MCP Swift SDK (
modelcontextprotocol/swift-sdk0.7.1+) - Platform: macOS 13+
- Auth: ES256 JWT signing via Apple CryptoKit
Architecture
Sources/AppStoreConnectMCP/
main.swift — Entry point: server setup + stdio transport
Configuration.swift — Loads env vars (ASC_ISSUER_ID, ASC_KEY_ID, ASC_PRIVATE_KEY_PATH)
Auth/JWTGenerator.swift — JWT token generation
API/
AppStoreConnectClient.swift — HTTP client with auto-retry on 401/429
Endpoints.swift — URL builders
Models/ — Codable request/response types (JSON:API format)
Tools/
ToolDefinitions.swift — MCP tool schemas (JSON Schema)
ToolRouter.swift — Dispatches tool calls to handlers
Handlers/ — One handler per tool
Available MCP Tools
list_apps, create_version, list_versions, update_version, add_localization, list_builds, attach_build, submit_for_review
Build & Run
tuist install # Fetch dependencies
tuist generate # Generate Xcode project
tuist build # Build via CLI
Or use ./bootstrap.sh which does all three and opens Xcode.
Adding a New Tool
- Add model in
API/Models/ - Add endpoint in
API/Endpoints.swift - Create handler in
Tools/Handlers/ - Register schema in
Tools/ToolDefinitions.swift+ add toallTools - Wire up in
Tools/ToolRouter.swift
Conventions
- All types are
Sendable(Swift 6 strict concurrency) - Handlers extract params from
CallTool.Parameters.argumentsdictionary - Tool output is plain text formatted for readability (e.g.,
[id] name (bundle_id)) - API responses follow Apple's JSON:API format — use
APIListResponse<T>/APIResponse<T>wrappers - Use
AppStoreConnectErrorfor error cases
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.
- 4d ago First seen · 68 lines · 591 tokens per session scan A 4fe63ba938c0
AppStoreConnectMCP AGENTS.md is an instructions file published in the GitHub repository Vvlladd/AppStoreConnectMCP (8 stars, last pushed 1mo ago), licensed MIT. It adds 591 tokens to every session, about $0.0030 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
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.