mcp-gsc is an MCP server that connects Google Search Console, a service for inspecting website search performance, to AI assistants so users can ask questions about SEO data in natural language. SEO professionals use it to analyze their Google Search Console data, and the catalogue entries provide related skills, a plugin, an instruction, and MCP configuration.
Borrowing it
Nothing to install: this file belongs to AminForou/mcp-gsc. 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/AminForou/mcp-gsc/main/CLAUDE.mdgit clone --depth 1 https://github.com/AminForou/mcp-gscWrote 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/aminforou/mcp-gsc/claude-md)<a href="https://agentmods.dev/instructions/aminforou/mcp-gsc/claude-md"><img src="https://agentmods.dev/badge/instructions/aminforou/mcp-gsc/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.
<a href="https://agentmods.dev/instructions/aminforou/mcp-gsc/claude-md"><img src="https://agentmods.dev/badge/instructions/aminforou/mcp-gsc/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00725 | $0.00725 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
mcp-gsc 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 9d 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- google-search-console-mcp CLAUDE.md — 100% identical, 0 lines differ
- mcp-gsc CLAUDE.md — 100% identical, 0 lines differ
- Google-Search-Console-GSC-MCP CLAUDE.md — 100% identical, 0 lines differ
- mcp-gsc-readonly CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Context for AI coding assistants (Claude, Cursor, Copilot, etc.) working in this repo.
What this is
MCP server that connects Google Search Console to AI assistants.
Single file: gsc_server.py (~1,670 lines). Built with FastMCP — no custom framework.
Running locally
uv sync
uv run python gsc_server.py
Auth
Two modes, tried in order:
- OAuth (default): Place
client_secrets.jsonin the repo root. On first run, a browser window opens for Google login. Token saved totoken.json(gitignored), auto-refreshes when expired. - Service account: Set
GSC_CREDENTIALS_PATHto the path of your service account JSON key file.
Set GSC_SKIP_OAUTH=true to force service account mode and skip OAuth entirely.
Key environment variables
| Variable | Default | Description |
|---|---|---|
MCP_TRANSPORT |
stdio |
Set to sse for remote/Docker/network use |
MCP_HOST |
127.0.0.1 |
Host to bind when MCP_TRANSPORT=sse |
MCP_PORT |
3001 |
Port to bind when MCP_TRANSPORT=sse |
GSC_DATA_STATE |
all |
all = matches GSC dashboard; final = confirmed data only (2–3 day lag) |
GSC_ALLOW_DESTRUCTIVE |
false |
Set true to enable add_site, delete_site, delete_sitemap |
GSC_CREDENTIALS_PATH |
— | Path to service account JSON key file |
GSC_OAUTH_CLIENT_SECRETS_FILE |
client_secrets.json |
Path to OAuth client secrets file |
GSC_SKIP_OAUTH |
false |
Set true to skip OAuth and use service account only |
Adding a new tool
- Add an
@mcp.tool()decorated async function anywhere ingsc_server.py - Use
get_gsc_service()for auth — it handles OAuth and service account automatically - Return
json.dumps(result)not formatted text strings (LLMs work better with structured data) - Handle
HttpErrorand return a plain string error message on failure
@mcp.tool()
async def my_new_tool(site_url: str) -> str:
"""One-line description shown to the AI as the tool's purpose."""
try:
service = get_gsc_service()
result = service.someApi().someMethod(siteUrl=site_url).execute()
return json.dumps(result)
except Exception as e:
if "404" in str(e):
return _site_not_found_error(site_url)
return f"Error: {str(e)}"
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.
- 9d ago First seen · 76 lines · 725 tokens per session scan A b1a4970b8048
mcp-gsc CLAUDE.md is an instructions file published in the GitHub repository AminForou/mcp-gsc (1,499 stars, last pushed 1mo ago), licensed MIT. It adds 725 tokens to every session, about $0.0036 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.