convez.ai
MCP ServerDados & AnalyticsIntermediário
AKzar1el

MCP Google Search Console

AKzar1el/mcp-gsc

Consulte performance SEO do Google Search Console via IA

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que conecta Claude, Cursor e outros clientes a dados do Google Search Console. Acesse impressões, cliques, rankings e status de indexação diretamente via IA, com autenticação Google OAuth segura. Pode ser hospedado em Cloudflare Workers sem necessidade de API keys.

Instalação

$npx convez-ai AKzar1el/mcp-gsc

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
8
Forks
2
Acompanhando
1
Saúde
85%
Último commit
há 1 dia
Versão
v0.4.41
Issues abertas
2
Contribuidores
2

Casos de uso

  • Análise de performance orgânica e top queries via conversa com IA
  • Monitoramento de status de indexação e saúde de sitemaps
  • Comparação de métricas entre períodos para identificar quedas de tráfego
  • Identificação de oportunidades rápidas (quick wins) em posições 5-15

Veredito

Integração técnica bem executada que democratiza acesso a dados GSC via IA, eliminando fricção de APIs. Ideal para profissionais SEO que querem análises conversacionais; hospedagem em Workers reduz custos operacionais.

README

A tradução para o português deste README ainda está na fila.

mcp-gsc

CI License: MIT MCP

A self-hostable Model Context Protocol (MCP) server for Google Search Console. Connect it to Claude.ai, Cursor, ChatGPT, or any MCP-compatible client and ask your AI assistant about your site's organic search performance — impressions, clicks, top queries, index status, and sitemap health — straight from your own Google account.

It runs on Cloudflare Workers and ships with one-click Google OAuth onboarding: connect the server in your client, sign in with Google once, grant read-only access to your Search Console properties, and you're done. No API keys to copy around, no service-account JSON to manage.

Prefer zero setup? The hosted version — with automatic weekly email digests delivered to your inbox — is at digestseo.com. This repository is the open-source core you can run yourself.

Tools

This server exposes five read-only tools:

ToolWhat it does
get_capabilitiesList every tool this server exposes and report whether your Google connection is currently authenticated (connected / not_connected). Takes no arguments — a good first call for discovery.
list_sitesList the Search Console properties the connected Google account can access (siteUrl, permissionLevel).
query_search_analyticsImpressions, clicks, CTR, and average position over a date range — broken down by query, page, country, device, date, or search appearance, with dimension filters, pagination (start_row), and a selectable search type (web, image, video, news, discover).
inspect_urlGoogle's URL Inspection report for a single page: index status, last crawl, mobile usability, rich-results eligibility, AMP.
list_sitemapsAll sitemaps submitted for a property, with submission/processing status and warning and error counts.

Every tool uses only the https://www.googleapis.com/auth/webmasters.readonly scope — the server never modifies your Search Console data. All tools carry the MCP readOnlyHint annotation, so clients can show them as safe.

What you can ask

Once connected, ask your assistant things like:

  • "What are my top 20 queries by clicks in the last 28 days?"
  • "Compare impressions for example.com this month vs last month — which pages dropped?"
  • "Is https://example.com/pricing indexed? When was it last crawled?"
  • "Which queries does my blog rank position 5–15 for? Those are my quick wins."
  • "Do any of my sitemaps have errors or warnings?"
  • "Split my clicks into brand vs non-brand using a regex on the query."
  • "How is my site doing in Google Discover vs regular web search?"

Connect in your AI client

Once you've deployed the server (see SETUP.md), connect it by pasting your Worker's /mcp URL into your client:

https://<your-worker>.workers.dev/mcp
  • Claude.ai — Settings → Connectors → Add custom connector → paste the /mcp URL. Leave Client ID and Client Secret blank. On first use, Claude opens a Google sign-in flow; grant read access and the connector turns green.
  • Cursor — add it as a custom MCP server pointing at the same /mcp URL.
  • ChatGPT (with connector/MCP support) — add a custom connector with the /mcp URL.

Any MCP-compatible client works — they all point at the same /mcp endpoint and share the same OAuth flow.

Setup

Self-hosting means bringing your own Google OAuth credentials and Cloudflare account. The full, copy-pasteable walkthrough is in SETUP.md — including an important note about Google's OAuth verification and the 7-day refresh-token limit while your app is unverified.

Quick shape:

git clone https://github.com/<you>/mcp-gsc.git
cd mcp-gsc
npm install
cp wrangler.example.jsonc wrangler.jsonc       # then paste in your KV ids
# set GOOGLE_CLIENT_ID / GOOGLE_CLIENT_SECRET / TOKEN_ENCRYPTION_KEY as secrets
npm run deploy

See SETUP.md for every step in detail.

Development

npm install
npm test              # typecheck + offline unit tests (what CI runs)
npm run dev           # wrangler dev (local)
npm run test:smoke    # structural smoke tests against a deployment

Contributions welcome — see CONTRIBUTING.md.

License

MIT © 2026 DigestSEO.


Built by the team behind digestseo.com — weekly SEO digests for non-technical site owners.

Ver o original no GitHub

Bom para

Relacionados