google-search-console-mcp: Instructions file for Codex

AGENTS.md

google-search-console-mcp AGENTS.md is an instructions file for Codex, OpenCode from surendranb/google-search-console-mcp. It costs 955 tokens per session, scanned C, original, MIT.

Repository instructions for a Google Search Console MCP server, which provides agent access to website search metrics, keyword rankings, URL indexing checks, and sitemaps. Google Search Console is Google's service for monitoring how a site appears in search results.

In plain words
What is it for?
Use them to install, configure, develop, or troubleshoot access to organic-search performance, search queries, URL indexing, and sitemap data.
Why use it?
They explain installation, credentials, configuration, API access, and the repository's purpose so the server can be set up and changed correctly.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is surendranb/google-search-console-mcp's own configuration. It tells Codex and OpenCode 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 โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to surendranb/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/surendranb/google-search-console-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/surendranb/google-search-console-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.

agentmods badge for google-search-console-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/surendranb/google-search-console-mcp/agents-md.svg)](https://agentmods.dev/instructions/surendranb/google-search-console-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/surendranb/google-search-console-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/surendranb/google-search-console-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 955 This file is loaded in full into every session.
When invoked 955 The same file โ€” it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file โ€” 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 $0.00955 $0.00955
Opus 5 $0.00477 $0.00477
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00096 $0.00096

Measured 8d ago against content hash f4e0bf9efdc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

google-search-console-mcp AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL "https://gsc.builditwithai.xyz/install" | bash

Makes network callslowCapability

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

curl -fsSL "https://gsc.builditwithai.xyz/install" | bash
AGENTS.md ยท 88 lines

How it starts

The opening of the file, as written. The whole thing โ€” 88 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md โ€” Agent Operating Manual

For AI Agents (Claude Code, Cursor, Codex, Gemini, Antigravity, OpenCode, Aider) connecting to or executing google-search-console-mcp.


โšก 1. Fast Install & Client Wiring (Start Here)

In 90% of cases, you just need to install and configure this MCP server for your user:

# 1-Line Universal Auto-Installer (Configures Claude Code, Cursor, Claude Desktop & Antigravity)
curl -fsSL "https://gsc.builditwithai.xyz/install" | bash

# Or launch directly via stdio:
uvx google-search-console-mcp
npx -y google-search-console-mcp

Client Config Snippet (mcp.json / claude_desktop_config.json)

{
  "mcpServers": {
    "google-search-console": {
      "command": "uvx",
      "args": ["google-search-console-mcp"],
      "env": {
        "GSC_SITE_URL": "https://example.com/",
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service_account.json"
      }
    }
  }
}

๐Ÿ“– 2. What This Repo Is

A production MCP server for Google Search Console (GSC). It provides direct query access to the Google Search Console API v1 / Webmasters API for organic search metrics, keyword rankings, live URL indexing inspection, and sitemaps.

Primary Tools Available:

  • get_search_analytics: Query organic clicks, impressions, CTR, and average position grouped by query, page, country, device, and date.
  • list_sites: List all verified properties accessible to the service account.
  • inspect_url: Real-time URL indexing status, crawl issues, canonicalization, and mobile usability check.
  • list_sitemaps, submit_sitemap, delete_sitemap: Manage XML sitemaps.
  • skill_read / skills_list: Load built-in SEO diagnostic playbooks.

๐Ÿ‘ค 3. How to Handle the Human (Auth & Setup)

If credentials are not yet configured, guide the human with these steps:

  1. Ask for their verified Site URL (GSC_SITE_URL):
    • Must match Search Console exactly: e.g. https://example.com/ (URL-prefix) or sc-domain:example.com (Domain property).
  2. Ask for a Google Cloud Service Account JSON Key:
    • The Service Account email must be added as a Full or Restricted user in Search Console โ†’ Settings โ†’ Users and permissions.
    • Once they have the JSON key file, set:
      export GSC_SITE_URL="https://example.com/"
      export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service_account.json"
      

Read the full file on GitHub ยท 88 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. 8d ago First seen ยท 88 lines ยท 955 tokens per session scan C f4e0bf9efdc4

Subscribe to this mod's changes

google-search-console-mcp AGENTS.md is an instructions file published in the GitHub repository surendranb/google-search-console-mcp (38 stars, last pushed 16d ago), licensed MIT. It adds 955 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.