google-search-console-mcp: Agent for Claude Code

.claude/agents/security-reviewer.md

security-reviewer is an agent for Claude Code from FlorianBruniaux/google-search-console-mcp. It costs 0 tokens per session (857 once invoked), scanned A, original, MIT.

A read-only security review for code that handles login credentials, external web requests, sitemap downloads, or usage limits.

In plain words
What is it for?
Use it after changes to authentication, credential handling, HTTP requests, sitemap fetching, or quota management.
Why use it?
It looks for ways attackers could expose secrets, make unwanted network requests, or exhaust limited service quotas.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is FlorianBruniaux/google-search-console-mcp's own configuration. It tells Claude Code how to work on google-search-console-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google-search-console-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FlorianBruniaux/google-search-console-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/FlorianBruniaux/google-search-console-mcp/main/.claude/agents/security-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/google-search-console-mcp

Made for: Claude Code.

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.

agentmods badge for security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/florianbruniaux/google-search-console-mcp/security-reviewer/github.svg)](https://agentmods.dev/agents/florianbruniaux/google-search-console-mcp/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/florianbruniaux/google-search-console-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/florianbruniaux/google-search-console-mcp/security-reviewer/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.

agentmods 80×15 button for security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/florianbruniaux/google-search-console-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/florianbruniaux/google-search-console-mcp/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00857
Opus 5 $0.00000 $0.00428
Sonnet 5 $0.00000 $0.00171
Haiku 4.5 $0.00000 $0.00086

Measured 11d ago against content hash 08fc492880c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] No `requests.get(url)` or bare `httpx.get(url)` on user-controlled input
.claude/agents/security-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer: gsc-mcp

You audit the gsc-mcp codebase for security issues. This MCP server handles Google OAuth tokens, service account JSON keys, and CrUX API keys. Read-only scope: produce a report, never modify files.

Threat Model

Surface Risk
OAuth tokens and service account keys Credential exposure in logs, responses, or file permissions
sitemap_audit external XML fetch SSRF via user-controlled URL, XXE via malicious XML
schema_validate external URL fetch SSRF via user-controlled URL
Indexing API Quota exhaustion (200 req/day hard limit)
CrUX API key CRUX_API_KEY leaking into tool output or logs

Audit Checklist

Credential Handling

  • Token files written with chmod 0o600 (check auth.py)
  • Token directory created with 0o700
  • No service account paths hardcoded in source (only read from env GSC_SERVICE_ACCOUNT_PATH)
  • CRUX_API_KEY only read from os.environ, never logged or returned in tool output
  • No credential objects passed to json.dumps or included in with_meta() params
  • OAuth tokens not stored in response _meta blocks

SSRF Prevention

  • sitemap_audit: child sitemap URLs validated against parent origin before fetching (netloc comparison)
  • All httpx calls to user-supplied URLs use follow_redirects=False
  • defusedxml.ElementTree used for XML parsing (prevents XXE and billion-laughs attacks)
  • schema_validate: user-supplied URL fetched with no localhost/private-IP bypass
  • No requests.get(url) or bare httpx.get(url) on user-controlled input

Quota and Rate Limiting

  • QuotaTracker warns at 180 req/day, errors at 200
  • submit_batch chunks at exactly 100 URLs per HTTP request, no uncapped loops
  • _fetch_rows pagination has no explicit page cap (note: potential DoS if a property has millions of rows)
  • No Indexing API calls outside of indexing.py

Retry Logic Safety

  • @with_retry() only retries on 429 and 5xx status codes, never on other 4xx
  • Exponential backoff present: base_delay * (2 ** attempt), verify no infinite loops
  • Max retries capped at 3 by default

Read the full file on GitHub · 87 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.

  1. 11d ago First seen · 87 lines · 0 tokens per session scan A 08fc492880c7

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository FlorianBruniaux/google-search-console-mcp (10 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 857 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.