Borrowing it
Nothing to install: this file belongs to mario-hernandez/google-seo-mcp-claude-code. 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/mario-hernandez/google-seo-mcp-claude-code/main/AGENTS.mdgit clone --depth 1 https://github.com/mario-hernandez/google-seo-mcp-claude-codeWrote 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/mario-hernandez/google-seo-mcp-claude-code/agents-md)<a href="https://agentmods.dev/instructions/mario-hernandez/google-seo-mcp-claude-code/agents-md"><img src="https://agentmods.dev/badge/instructions/mario-hernandez/google-seo-mcp-claude-code/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 5.1 | $0.07360 | $0.07360 |
| Opus 5 | $0.03680 | $0.03680 |
| Sonnet 5 | $0.01472 | $0.01472 |
| Haiku 4.5 | $0.00736 | $0.00736 |
Grade A, and why
google-seo-mcp-claude-code 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 8d 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Operator's Guide
Drop this file into your agent's context (Claude Code, Cursor, Windsurf) to maximize what the MCP can do. It's the synthesis of three expert perspectives — technical SEO, local SEO + SERP intent, and marketing/growth analytics — into one operating manual.
Table of contents
- Mental model — the seven commandments
- Tool inventory
- Playbooks — when the user says X, run Y
- Decision trees
- Anti-patterns — what the agent must NOT do
- Argument cookbook
- Inference workarounds — what this MCP doesn't measure but you can infer
- Reporting templates
- Edge cases
- Output formatting rules
1. Mental model — the seven commandments
- Provenance first. Every tool returns
{"data": ..., "_meta": {source, site_url|property, period, fetched_at}}. Quote a number → quote its_meta.periodand_meta.sourcewith it. Cross-platform tools cite TWO periods (GSC has 3-day lag, GA4 has 1-day lag) — quote both. - Cross-platform > single-source. The 6
cross_*tools are the differentiators. Use them first for anything multi-faceted (ROI, attribution, journey, prioritization). Drop intogsc_*/ga4_*only for surgical follow-up. - Diagnoses, not data dumps. Tools like
gsc_traffic_dropsreturn classifications (ranking_loss,ctr_collapse,demand_decline). Pass these through; don't replace with your own narrative. - Sessions are vanity. Revenue is sanity. Never report "organic up 40%" without
cross_seo_to_revenue_attribution. If revenue didn't move, the win isn't real — it's brand search, bots, or misattributed direct. - Don't extrapolate. GSC 3-day lag means a 7-day window is really 4 usable days. If a tool returns
min_metric_p3 < threshold, the row is statistical noise — flag it, don't rank it. - Read-only by default. Destructive ops (sitemap submission) require
GSC_ALLOW_DESTRUCTIVE=true. Even when enabled, ask the user before submitting. - This MCP is GSC + GA4 only. No GMB API, no SERP scraper, no AI Overview detector. SERP feature impact must be inferred from click-impression-CTR patterns combined with
resource://algorithm-updates— see §7 workarounds.
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.
- 8d ago First seen · 458 lines · 7,360 tokens per session scan A 3a9db072d4ac
google-seo-mcp-claude-code AGENTS.md is an instructions file published in the GitHub repository mario-hernandez/google-seo-mcp-claude-code (11 stars, last pushed 4mo ago), licensed MIT. It adds 7,360 tokens to every session, about $0.0368 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.