Borrowing it
Nothing to install: this file belongs to pijusz/mcp-gsc. 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/pijusz/mcp-gsc/master/AGENTS.mdgit clone --depth 1 https://github.com/pijusz/mcp-gscWrote 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/pijusz/mcp-gsc/agents-md)<a href="https://agentmods.dev/instructions/pijusz/mcp-gsc/agents-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-gsc/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/pijusz/mcp-gsc/agents-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-gsc/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 | $0.00961 | $0.00961 |
| Opus 5.5 | $0.00384 | $0.00384 |
| Sonnet 5.5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
mcp-gsc 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 14d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for mcp-gsc
Project Structure
src/
├── index.ts # Entry point (stdio transport + setup dispatch)
├── server.ts # McpServer creation + tool registration
├── auth/
│ ├── index.ts # Auth router + getAuthHeaders() (just Bearer token)
│ ├── oauth.ts # OAuth 2.0 token load/refresh
│ ├── service-account.ts # Service account JWT auth
│ └── setup.ts # Interactive credential + config helper
├── config/
│ └── env.ts # Zod-validated env vars + .env file loading
├── services/
│ ├── gsc-api.ts # Central REST client with retry logic
│ ├── format.ts # Markdown table / CSV formatters
│ ├── rate-limiter.ts # URL Inspection rate tracking (600 QPM + 2K/day)
│ └── property-resolver.ts # Auto-resolve GSC property format
├── tools/
│ ├── index.ts # Barrel: registers all tools on server
│ ├── sites.ts # list_properties, get_property_details
│ ├── analytics.ts # search_analytics (core)
│ ├── sitemaps.ts # list_sitemaps, get_sitemap + write tools
│ ├── inspection.ts # inspect_url, batch_inspect_urls
│ ├── export.ts # export_csv
│ ├── sites-write.ts # add_site, delete_site (gated)
│ ├── reporting.ts # performance_overview, compare_periods, top_movers, device_country_breakdown
│ ├── seo.ts # quick_wins, cannibalization, opportunity_finder, position_tracking, ctr_anomalies, content_decay, weekly_seo_report
│ └── technical.ts # indexing_coverage, sitemap_health
└── utils/
├── register-tool.ts # readTool/writeTool: registerTool + MCP annotations
├── logger.ts # stderr-only logger
└── property.ts # URL encoding, domain extraction, brand name extraction
Authentication
Two methods (auto-detected from credentials file):
- OAuth 2.0 — Run
bun run setupto authorize interactively - Service Account — Auto-detected if credentials file has
type: "service_account"
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.
- 14d ago Changed · +1 lines · +91 tokens per session 76f7aed115f4
- 2mo ago First seen · 75 lines · 870 tokens per session scan A d950591178b1
mcp-gsc AGENTS.md is an instructions file published in the GitHub repository pijusz/mcp-gsc (3 stars, last pushed 15d ago), licensed MIT. It adds 961 tokens to every session, about $0.0038 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.
mcp-gsc AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-gsc AGENTS.mdpijusz/mcp-gsc | Instructions file | 3 | 15d ago | MIT | A | 961 | 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 |