Borrowing it
Nothing to install: this file belongs to desunit/google-play-analytics-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/desunit/google-play-analytics-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/desunit/google-play-analytics-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/desunit/google-play-analytics-mcp/agents-md)<a href="https://agentmods.dev/instructions/desunit/google-play-analytics-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/desunit/google-play-analytics-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/desunit/google-play-analytics-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/desunit/google-play-analytics-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 | $0.00991 | $0.00991 |
| Opus 5.5 | $0.00396 | $0.00396 |
| Sonnet 5.5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
google-play-analytics-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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) working in this repository. CLAUDE.md is a
symlink to this file.
What this is
An MCP server (server.py + gp_client.py) that reads Google Play Console bulk
CSV reports from a developer's Cloud Storage bucket (pubsite_prod_rev_*) and
exposes them as analytics tools. Python 3.11+, stdlib + mcp, google-auth,
requests. No build step; run server.py over stdio.
gp_client.py— auth (service-account → Storage token), bucket list/download with caching, BOM-aware decode, CSV parse, theFAMILIESspec, and aggregation helpers.server.py— the FastMCP tool surface. Tools shapefetch_family()output into compact aggregated responses.
Hard rules
- Never commit secrets or business data. The service-account key
(
google-play.json/*-service-account*.json),apps.json, and the.cache/+reports/report data are all gitignored. Before any commit, rungit statusand confirm none are staged. This repo is public. - No org-specific values in committed code. The reports bucket, the
service-account, and app aliases are supplied at runtime via env vars
(
GOOGLE_PLAY_REPORTS_BUCKET,GOOGLE_PLAY_SA_JSON,GOOGLE_PLAY_APP_ALIASES) or gitignored local files — never hardcoded. - Read-only. The service account uses
devstorage.read_only. This server must never write to the bucket or to Play Console. Don't add write scopes or mutating tools. - Be honest about coverage. Google discontinued some bulk reports
(
retained_installers,buyers_7dafter 2021-06;ratings_v2was 2022–2023 only). Keep thedescfields and README coverage table accurate; flag historical-only families rather than implying live data. - Never serve an unvalidated cache. Play rewrites the current month's
file daily, so a cache keyed on filename alone silently returns a truncated
month.
download_object()revalidates against the object's bucket-sideupdated/sizeplus the on-disk byte length on every read; keep it that way. Any new fetch path must go through it, not a bare_request(). - Every response must carry
coverage.fetch_family()computesdata_through/days_present/missing_datesand warns on days missing inside the range;_meta()inserver.pypasses it through. Without it a caller comparing two windows can unknowingly compare 7 days against 4 and read a reporting hole as a real decline. Don't drop it to save tokens.
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.
- 1mo ago Changed · +10 lines · +189 tokens per session 002c74f7cb55
- 2mo ago First seen · 70 lines · 802 tokens per session scan A 9c5c1f4a577f
google-play-analytics-mcp AGENTS.md is an instructions file published in the GitHub repository desunit/google-play-analytics-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 991 tokens to every session, about $0.0040 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.
google-play-analytics-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| google-play-analytics-mcp AGENTS.mddesunit/google-play-analytics-mcp | Instructions file | 0 | 1mo ago | MIT | A | 991 | 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 |