What is gsc-ga4-mcp CLAUDE.md?

A set of instructions for an MCP server that gives Claude Code read-only access to Google Search Console and Google Analytics 4. Search Console reports how a site appears in Google Search, while Analytics 4 reports website or app usage; the server can join their data by URL path.

It is for checking search performance, website or app analytics, and combined reports, using a domain name mapped to the relevant Google properties.

It removes the need to switch between these two Google services for supported reports. Read-only access also means the described connection is for viewing data, not changing it.

How delaren47/gsc-ga4-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to delaren47/gsc-ga4-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/delaren47/gsc-ga4-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/delaren47/gsc-ga4-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/delaren47/gsc-ga4-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/delaren47/gsc-ga4-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/delaren47/gsc-ga4-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/delaren47/gsc-ga4-mcp/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/delaren47/gsc-ga4-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/delaren47/gsc-ga4-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,130 This file is loaded in full into every session.

When invoked 1,130 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01130	$0.01130
Opus 5	$0.00565	$0.00565
Sonnet 5	$0.00226	$0.00226
Haiku 4.5	$0.00113	$0.00113

Measured 5d ago against content hash 4ed3a93a43c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gsc-ga4-mcp CLAUDE.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 5d 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.

CLAUDE.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gsc-ga4-mcp

Local MCP server that gives Claude Code read-only access to Google Search Console and GA4 over stdio. It exposes 20 tools — GSC-only, GA4-only, and combined tools that join the two datasets by URL path — plus a project-mapping lookup so a prompt can name a domain instead of a raw property ID. It runs on this machine, calls Google's APIs directly, and has no database, backend, or telemetry.

Commands

npm install then npm run build (tsc → dist/). dist/ is gitignored, so a fresh clone has no runnable entry point until this is done.
npm run dev — tsx src/index.ts, runs the server from TypeScript with no build. It speaks MCP over stdio, so run by hand it just waits on stdin; that is not a hang.
npm start — node dist/index.js. The same command Claude Code launches.
npm run auth — one-time OAuth. Listens on 127.0.0.1:3000 (OAUTH_PORT overrides), prints a Google consent URL, writes the token to GOOGLE_TOKEN_PATH.
There is no test suite and no test script. Do not invent npm test. npm run build is the only automated check — TypeScript strict type errors are the gate.

Architecture and constraints

TypeScript, ESM ("type": "module", module: NodeNext). Intra-src/ imports must carry the .js extension.
Read-only is enforced by OAuth scope, not by a code-level write guard: SCOPES in src/config.ts requests only webmasters.readonly and analytics.readonly. Several read endpoints are POSTs (searchAnalytics/query, :runReport, urlInspection) — POST here does not mean write. IMPORTANT: never widen SCOPES when adding a tool.
Credentials never live in the repo. .env (gitignored, present locally) supplies the names only: GOOGLE_AUTH_MODE (oauth | service_account), GOOGLE_OAUTH_CREDENTIALS_FILE, GOOGLE_TOKEN_PATH, GOOGLE_OAUTH_REDIRECT_URI, GOOGLE_SERVICE_ACCOUNT_KEY_FILE, PROJECTS_CONFIG, MCP_DEFAULT_GSC_SITE, MCP_DEFAULT_GA4_PROPERTY, MAX_ROWS. The files those point at sit in ~/.config/gsc-ga4-mcp/.
Never read .env, token.json, oauth-client.json, a service-account key, or the real projects.json into a transcript, a commit, or a document. Edit the .example files instead.
Every path in .env must be absolute. ~ is not expanded anywhere in the code.
projects.json (located by PROJECTS_CONFIG) maps a project/client/domain name to its gscSiteUrl and ga4Property, which is what project_lookup and project_mappings read. It is gitignored because it holds real client property IDs; projects.example.json is the committed template. Lookup matches name, domain or client by case-insensitive substring.

Read the full file on GitHub · 43 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.

5d ago First seen · 43 lines · 1,130 tokens per session scan A 4ed3a93a43c8

Subscribe to this mod's changes

gsc-ga4-mcp CLAUDE.md is an instructions file published in the GitHub repository delaren47/gsc-ga4-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 1,130 tokens to every session, about $0.0056 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 2026-09-07.

Analytics and metrics Marketing and SEO

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

gsc-ga4-mcp: Instructions file for Claude Code