gsc-mcp-server: Instructions file for Claude Code

AGENTS.md

gsc-mcp-server AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Klartika/gsc-mcp-server. It costs 2,015 tokens per session, scanned A, original, MIT.

Repository instructions for developers and coding agents working on a fork of a Google Search Console tool. Google Search Console is a service that reports how websites appear in Google Search.

In plain words
What is it for?
It is for guiding maintenance, code changes, security reviews, and deployment of the local or optional remote Google Search Console server.
Why use it?
It explains the fork's structure, security rules, and changes while helping contributors avoid breaking the original project or exposing credentials.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is Klartika/gsc-mcp-server's own configuration. It tells Claude Code, Codex and OpenCode how to work on gsc-mcp-server 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 gsc-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Klartika/gsc-mcp-server. 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/Klartika/gsc-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Klartika/gsc-mcp-server

Made for: Claude Code, 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 gsc-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/klartika/gsc-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/klartika/gsc-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/klartika/gsc-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/klartika/gsc-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,015 This file is loaded in full into every session.
When invoked 2,015 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02015 $0.02015
Opus 5 $0.01007 $0.01007
Sonnet 5 $0.00403 $0.00403
Haiku 4.5 $0.00201 $0.00201

Measured 6d ago against content hash 6719e06a2cc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gsc-mcp-server 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 6d 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.

AGENTS.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — maintenance guide

Guidance for humans and AI coding agents working on this fork of AminForou/mcp-gsc. Read this before making changes.

What this fork adds

Upstream is a local (stdio) MCP server for Google Search Console. This fork adds an optional remote, OAuth 2.1-protected HTTP transport: a self-hostable server where each user signs in with their own Google account (webmasters.readonly) — no service accounts, no credential files on disk. It is built on the MCP Python SDK's OAuth framework (mcp.server.auth), federates to Google, persists sessions in SQLite, and ships as a container image.

All of this lives in new files under gsc_remote/. The upstream server and its tools are unchanged.

Hard rules (do not break these)

  1. Public repository — no identifiable information. Never commit real domains, emails, hostnames, company names, secrets or tokens. Use only RFC-reserved placeholders (example.com, <your-host>). Deployment values are supplied only via environment variables set by the deployment.

  2. Stay rebaseable on upstream. Do not edit gsc_server.py. Put all fork behaviour in gsc_remote/. The seams into upstream are runtime monkeypatches, not source edits. Periodically: git fetch upstream && git rebase upstream/main.

    This repository is not a GitHub fork — it shares upstream's history but not its fork network, so there is no "Sync fork" button and gh repo sync does not apply. The upstream remote above is the only route, and it works exactly as it would in a fork. A scheduled agent checks this weekly.

    Documented exceptions, all cheap to re-apply, all for the same reason — upstream ships artefacts describing a local server this fork does not deploy:

    • README.md: the orientation banner at the top, and the removal of upstream's advertisements for a competing hosted GSC MCP service.
    • Deleted: .claude-plugin/, .cursor-plugin/, .mcp.json, mcp.json. They configure uvx mcp-search-console — the local stdio server authenticated by credential files — so installing the plugin would stand up a second GSC server with different auth beside the remote connector this fork exists to provide. They also carry upstream's author and a homepage pointing at the same hosted service. Without a marketplace.json they were never installable as a plugin anyway.
    • CLAUDE.md: a fork banner pointing here, plus corrections to the three sections that actively misdirect — it told assistants to add tools to gsc_server.py (rule 2), gave a test command that skips tests/remote/, and documented only upstream's image. The rest is upstream's and still describes the local server accurately.
    • skills/indexing-audit/SKILL.md: a one-word bug fix, also sent upstream.

Read the full file on GitHub · 153 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. 6d ago First seen · 153 lines · 2,015 tokens per session scan A 6719e06a2cc9

Subscribe to this mod's changes

gsc-mcp-server AGENTS.md is an instructions file published in the GitHub repository Klartika/gsc-mcp-server (0 stars, last pushed 19d ago), licensed MIT. It adds 2,015 tokens to every session, about $0.0101 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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 · 7,104 tokens