What is appstore-mcp AGENTS.md?

Project instructions for an MCP server that researches competing apps using public Apple App Store data.

Use them when developing or testing app searches, app details, comparisons, charts, reviews, review summaries, screenshots, or competitor-comparison prompts.

They describe the server's supported tools, development commands, architecture, dependencies, and project decisions so changes stay within its scope.

How LaurMost/appstore-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to LaurMost/appstore-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/LaurMost/appstore-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/LaurMost/appstore-mcp

Made for: Codex, OpenCode.

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/laurmost/appstore-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/laurmost/appstore-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/laurmost/appstore-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/laurmost/appstore-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/laurmost/appstore-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/laurmost/appstore-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 885 This file is loaded in full into every session.

When invoked 885 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	$0.00885	$0.00885
Opus 5.5	$0.00354	$0.00354
Sonnet 5.5	$0.00177	$0.00177
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash 2a4b215a9c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

appstore-mcp 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 2mo 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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

appstore-mcp

Open-source MCP server for live Apple App Store competitor research. Python 3.12, uv, fastmcp. Design record: CONTEXT.md (domain glossary) + docs/adr/ (decisions) — see docs/agents/domain.md. There is no PLAN.md; the original v1 design doc was fully redistributed into ADRs, CONTEXT.md, and this file once the decisions it recorded had settled.

Depend on the fastmcp package (jlowin's actively-developed one) — not the frozen FastMCP bundled in the official mcp SDK. mcp[cli] is not a dependency; don't reintroduce it.

Local dev server: fastmcp dev (Inspector UI, stdio) or fastmcp run (standalone), driven by fastmcp.json — see README's Development section.

Tool surface

7 read-only MCP tools over public Apple App Store data (search_app_store, get_app_store_app, compare_app_store_apps, get_app_store_charts, get_app_store_reviews, digest_app_store_reviews, get_app_store_screenshots), plus one prompt, compare_competitors. Tool orchestration lives in src/appstore_mcp/tools/ (one module per tool), server.py stays thin registrations, and apple/ stays single-source API clients per upstream domain — see docs/adr/0002-tools-package-for-orchestration.md for why. This list will drift as tools are added; server.py's @mcp.tool decorators are the source of truth for exact signatures, not this file.

Conventions for any new tool:

readOnlyHint: true, idempotentHint: true, openWorldHint: true annotations; an explicit timeout; numeric limits as Annotated[int, Field(ge=..., le=...)], never manual clamping; a Google-style Args: docstring section so FastMCP generates per-parameter schema descriptions.
Compact, normalized response by default — raw upstream payloads are opt-in only (docs/adr/0004-compact-response-shape-with-raw-opt-in.md).
Failures follow the two-tier split in docs/adr/0006-two-tier-failure-semantics.md: a broken promise raises; in-band degradation returns success plus meta.warnings/per-item errors.

Read the full file on GitHub · 76 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.

2mo ago First seen · 76 lines · 885 tokens per session scan A 2a4b215a9c21

Subscribe to this mod's changes

appstore-mcp AGENTS.md is an instructions file published in the GitHub repository LaurMost/appstore-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 885 tokens to every session, about $0.0035 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.

Research

appstore-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
appstore-mcp AGENTS.mdLaurMost/appstore-mcp	Instructions file	0	3mo ago	MIT	A	885	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

appstore-mcp: Instructions file for Codex