mcp-server-google-search-console

mcp-server-google-search-console

Enables interaction with Google Search Console via MCP, offering search analytics, performance summaries, URL inspection, sitemap management, and property listing for SEO workflows.

Category
访问服务器

README

mcp-server-google-search-console

CI Node.js >= 22 MCP compatible License: MIT npm version npm downloads

Community-built MCP server for the Google Search Console API. Provides search analytics, performance summaries, URL inspection, sitemap management, and property listing through the Model Context Protocol.

Features

  • 9 tools covering search analytics, performance summaries, URL inspection, sitemap management, and property listing
  • 3 prompts for guided multi-step SEO workflows
  • 2 resources for automatic property and sitemap discovery
  • Service Account & OAuth — choose headless or interactive authentication
  • Read-only by default — write tools are only registered when write scope is configured
  • Safety gatesdelete_sitemap requires explicit confirm: true
  • Minimal dependencies — only @modelcontextprotocol/sdk and zod

Quick Start

1. Set Up Credentials

Service Account (recommended for servers & CI):

  1. Go to Google Cloud Console
  2. Create or select a project
  3. Enable the Google Search Console API
  4. Create a Service Account and download the JSON key file
  5. In Google Search Console, add the service account email as a user to your properties

OAuth (recommended for personal use):

  1. In Google Cloud Console, create OAuth 2.0 Client ID (type: Desktop app)
  2. Download the client credentials JSON
  3. Set GSC_OAUTH_CLIENT_FILE — the server will open a browser for consent on first run
  4. Tokens are cached at ~/.config/gsc-mcp/oauth-token.json (or GSC_OAUTH_TOKEN_FILE)

2. Configure Your Client

<details open> <summary><strong>Claude Code</strong></summary>

claude mcp add google-search-console \
  -e GSC_SERVICE_ACCOUNT_KEY_FILE=/path/to/service-account-key.json \
  -- npx -y mcp-server-google-search-console

Or add to .mcp.json manually:

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "mcp-server-google-search-console"],
      "env": {
        "GSC_SERVICE_ACCOUNT_KEY_FILE": "/path/to/service-account-key.json"
      }
    }
  }
}

</details>

<details> <summary><strong>Claude Desktop</strong></summary>

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "mcp-server-google-search-console"],
      "env": {
        "GSC_SERVICE_ACCOUNT_KEY_FILE": "/path/to/service-account-key.json"
      }
    }
  }
}

</details>

<details> <summary><strong>Cursor</strong></summary>

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "mcp-server-google-search-console"],
      "env": {
        "GSC_SERVICE_ACCOUNT_KEY_FILE": "/path/to/service-account-key.json"
      }
    }
  }
}

</details>

<details> <summary><strong>VS Code / Copilot</strong></summary>

Add to .vscode/mcp.json:

{
  "servers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "mcp-server-google-search-console"],
      "env": {
        "GSC_SERVICE_ACCOUNT_KEY_FILE": "/path/to/service-account-key.json"
      }
    }
  }
}

</details>

<details> <summary><strong>Docker</strong></summary>

docker build -t gsc-mcp .
{
  "mcpServers": {
    "google-search-console": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-e", "GSC_SERVICE_ACCOUNT_KEY_FILE=/key.json",
        "-v", "/path/to/service-account-key.json:/key.json:ro",
        "gsc-mcp"
      ]
    }
  }
}

</details>

Tools

Always available (read-only scope)

Tool Description
list_sites List all GSC properties accessible by the current credentials
get_site Get details for a specific property (permission level, verification)
get_search_analytics Query search performance data with dimensions, filters, date ranges, and comparison mode
get_performance_summary Quick performance overview: current vs previous period metrics, deltas, and top 10 queries in a single call
inspect_url Check a URL's indexing status, mobile usability, and rich results
batch_inspect_urls Inspect multiple URLs concurrently (up to 20) with a single call
list_sitemaps List all sitemaps for a property with aggregated health summary

Write scope required

These tools are only registered when GSC_SCOPES includes the full write scope. They do not appear in the tool list otherwise.

Tool Description
submit_sitemap Submit a sitemap to Google
delete_sitemap Delete a sitemap (requires confirm: true safety gate)

Prompts

Guided multi-step SEO workflows that guide LLMs through structured analysis.

Prompt Parameters Description
seo_performance_analysis site_url, period (7d/28d/90d) 5-step analysis: Top Queries → Top Pages → Device Split → Country Split → Trends. Produces a structured report with actionable insights.
index_coverage_check site_url, urls (comma-separated) Batch URL inspection with structured coverage report — flags indexing issues, canonical mismatches, and mobile problems.
content_opportunity_analysis site_url Full-funnel analysis: Low-Hanging Fruit (positions 5–20), Keyword Cannibalization detection, and Trending queries via comparison mode.

Resources

URI Description
sites://list Auto-discovery of all GSC properties accessible with current credentials. Enables LLMs to discover available sites without calling list_sites first.
sitemaps://{site_url} Sitemaps for a specific property (e.g. sitemaps://sc-domain:example.com) with health summary, errors, warnings, and index rates.

Environment Variables

Variable Required Description
GSC_SERVICE_ACCOUNT_KEY_FILE * Path to service account JSON key file
GSC_SERVICE_ACCOUNT_KEY * Inline service account JSON (alternative to file)
GSC_OAUTH_CLIENT_FILE * Path to OAuth client credentials JSON (Desktop app type)
GSC_OAUTH_TOKEN_FILE No Custom path for cached OAuth tokens (default: ~/.config/gsc-mcp/oauth-token.json)
GSC_SCOPES No OAuth scope. Default: webmasters.readonly. Set to https://www.googleapis.com/auth/webmasters for write access

* Auth priority: OAuth (GSC_OAUTH_CLIENT_FILE) > Service Account (GSC_SERVICE_ACCOUNT_KEY_FILE or GSC_SERVICE_ACCOUNT_KEY). At least one must be configured.

Development

npm install      # Install dependencies
npm run build    # Build
npm run dev      # Watch mode
npm test         # Run tests

License

MIT

Note: This is an unofficial community project. It is not affiliated with or endorsed by Google.


Built by Tobias Hein at artaxo — a digital marketing agency specializing in AI Search Optimization.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选