convez.ai
MCP ServerDados & AnalyticsIntermediário
ahonn

Google Search Console MCP Server

ahonn/mcp-server-gsc

Acesso programático aos dados do Google Search Console via MCP

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que fornece acesso completo aos dados do Google Search Console com capacidades avançadas de análise. Permite recuperar até 25 mil linhas de dados de performance com filtros regex, detecção automática de oportunidades de otimização e análise multidimensional (query, página, país, dispositivo, aparência de busca).

Instalação

$npx convez-ai ahonn/mcp-server-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
286
Forks
56
Acompanhando
6
Saúde
28%
Último commit
há 2 meses
Versão
—
Issues abertas
1
Contribuidores
6

Casos de uso

  • Análise de performance SEO em larga escala
  • Identificação automática de oportunidades de otimização (quick wins)
  • Monitoramento de métricas de busca por dimensões múltiplas
  • Relatórios customizados com filtros avançados e regex
  • Integração de dados GSC em workflows de automação com Claude

Veredito

Solução bem implementada para quem precisa de acesso programático ao GSC. Excelente para automação de análises SEO e detecção de insights, mas requer configuração adequada de credenciais Google Cloud — recomendado para usuários com experiência em autenticação de APIs.

README

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

Google Search Console MCP Server

A Model Context Protocol (MCP) server providing comprehensive access to Google Search Console data with enhanced analytics capabilities.

Features

  • Enhanced Search Analytics: Retrieve up to 25,000 rows of performance data
  • Advanced Filtering: Support for regex patterns and multiple filter operators
  • Quick Wins Detection: Automatically identify optimization opportunities
  • Rich Dimensions: Query, page, country, device, and search appearance analysis
  • Flexible Date Ranges: Customizable reporting periods with historical data access

Sponsored by

macuse.app is a native macOS application that gives your AI superpowers by integrating AI assistants with macOS apps like Calendar, Mail, and Notes, plus universal UI control for any application. Supports Claude Desktop, Cursor, and Raycast with one-click setup. Privacy-first, runs locally.

Prerequisites

  • Node.js 18 or later
  • Google Cloud Project with Search Console API enabled
  • Service Account credentials with Search Console access

Installation

npm install mcp-server-gsc

Authentication Setup

To obtain Google Search Console API credentials:

  1. Visit the Google Cloud Console
  2. Create a new project or select an existing one
  3. Enable the API:
  1. Create credentials:
  • Navigate to "APIs & Services" > "Credentials"
  • Click "Create Credentials" > "Service Account"
  • Fill in the service account details
  • Create a new key in JSON format
  • The credentials file (.json) will download automatically
  1. Grant access:

Usage

Claude Desktop Configuration

{
  "mcpServers": {
    "gsc": {
      "command": "npx",
      "args": ["-y", "mcp-server-gsc"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/credentials.json"
      }
    }
  }
}

Available Tools

search_analytics

Get comprehensive search performance data from Google Search Console with enhanced analytics capabilities.

Required Parameters:

  • siteUrl: Site URL (format: http://www.example.com/ or sc-domain:example.com)
  • startDate: Start date (YYYY-MM-DD)
  • endDate: End date (YYYY-MM-DD)

Optional Parameters:

  • dimensions: Comma-separated list (query, page, country, device, searchAppearance, date)
  • type: Search type (web, image, video, news, discover, googleNews)
  • aggregationType: Aggregation method (auto, byNewsShowcasePanel, byProperty, byPage)
  • rowLimit: Maximum rows to return (default: 1000, max: 25000)
  • dataState: Data freshness (all or final, default: final)

Filter Parameters:

  • pageFilter: Filter by page URL (supports regex with regex: prefix)
  • queryFilter: Filter by search query (supports regex with regex: prefix)
  • countryFilter: Filter by country ISO 3166-1 alpha-3 code (e.g., USA, CHN)
  • deviceFilter: Filter by device type (DESKTOP, MOBILE, TABLET)
  • searchAppearanceFilter: Filter by search feature (e.g., AMP_BLUE_LINK, AMP_TOP_STORIES)
  • filterOperator: Operator for filters (equals, contains, notEquals, notContains, includingRegex, excludingRegex)

Quick Wins Detection:

  • detectQuickWins: Enable automatic detection of optimization opportunities (default: false)
  • quickWinsConfig: Configuration for quick wins detection:
    • positionRange: Position range to consider (default: [4, 20])
    • minImpressions: Minimum impressions threshold (default: 100)
    • minCtr: Minimum CTR percentage (default: 1)

Example - Basic Query:

{
  "siteUrl": "https://example.com",
  "startDate": "2024-01-01",
  "endDate": "2024-01-31",
  "dimensions": "query,page",
  "rowLimit": 5000
}

Example - Advanced Filtering with Regex:

{
  "siteUrl": "https://example.com",
  "startDate": "2024-01-01",
  "endDate": "2024-01-31",
  "dimensions": "page,query",
  "queryFilter": "regex:(AI|machine learning|ML)",
  "filterOperator": "includingRegex",
  "deviceFilter": "MOBILE",
  "rowLimit": 10000
}

Example - Quick Wins Detection:

{
  "siteUrl": "https://example.com",
  "startDate": "2024-01-01",
  "endDate": "2024-01-31",
  "dimensions": "query,page",
  "detectQuickWins": true,
  "quickWinsConfig": {
    "positionRange": [4, 15],
    "minImpressions": 500,
    "minCtr": 2
  }
}

License

MIT

Contributing

Contributions are welcome! Please read our contributing guidelines before submitting pull requests.

Ver o original no GitHub

Bom para

Relacionados