Google Search Console MCP Server

Google Search Console MCP Server

Provides AI agents with read-only access to Google Search Console data, including search analytics, index coverage, and sitemap status. It enables users to query clicks, impressions, and ranking performance or check URL indexing status through natural language.

Category
访问服务器

README

Google Search Console MCP Server

A Model Context Protocol (MCP) server that gives AI agents direct access to your Google Search Console data.

  • Search analytics — query clicks, impressions, CTR, and average position by page, query, country, device, or date range
  • Compare periods — week-over-week, month-over-month trends
  • Find opportunities — high-impression/low-click queries, ranking keywords you didn't know about
  • Track specific pages — see which URLs are gaining or losing traction
  • Index coverage — check which pages are indexed, excluded, or erroring
  • Sitemap status — verify sitemaps are being read and how many URLs are indexed

Read-only access — this server cannot submit URLs, modify settings, or make any changes to your Search Console properties.

[!IMPORTANT] This server uses service account authentication. The service account must be added as a user on each Search Console property you want to access.

Tools

<details> <summary><code>list_sites</code></summary>

List all sites (properties) you have access to in Google Search Console.

No parameters required. </details>

<details> <summary><code>search_analytics</code></summary>

Query search analytics data — clicks, impressions, CTR, and position.

Parameter Type Required Description
siteUrl string Yes Site URL as it appears in Search Console (e.g. https://example.com/ or sc-domain:example.com)
startDate string Yes Start date in YYYY-MM-DD format
endDate string Yes End date in YYYY-MM-DD format
dimensions string No Comma-separated: query, page, country, device, searchAppearance, date
rowLimit number No Max rows to return (default 100, max 25000)
searchType string No web, image, video, news, discover, or googleNews (default web)
queryFilter string No Filter by query. Prefix with regex: for regex matching
pageFilter string No Filter by page URL. Prefix with regex: for regex matching
countryFilter string No ISO 3166-1 alpha-3 country code (e.g. USA, GBR)
deviceFilter string No DESKTOP, MOBILE, or TABLET
</details>

<details> <summary><code>inspect_url</code></summary>

Check indexing status, crawl info, and mobile usability for a URL.

Parameter Type Required Description
siteUrl string Yes Site URL as it appears in Search Console
inspectionUrl string Yes The full URL to inspect (must belong to the site)
</details>

<details> <summary><code>list_sitemaps</code></summary>

List all submitted sitemaps and their status for a site.

Parameter Type Required Description
siteUrl string Yes Site URL as it appears in Search Console
</details>

Installation

Quick setup via agent

Already have your service account key? Paste this prompt into Claude Code or Claude Desktop and it will configure everything for you:

Clone and build the Google Search Console MCP server from https://github.com/sarahpark/google-search-console-mcp, then add it to my global MCP config. My service account key is at /path/to/service-account-key.json. After setup, call list_sites to verify it works.

Replace the key path with your actual file location.

Build from source

git clone https://github.com/sarahpark/google-search-console-mcp.git
cd google-search-console-mcp
npm install
npm run build

Configuration

Google Cloud setup: service account key

  1. Go to Google Cloud Console and create a new project (or select an existing one)
  2. Open the Search Console API page and click Enable
  3. In the sidebar, go to APIs & Services → Credentials
  4. Click Create Credentials → Service account
  5. Give it a name (e.g. "search-console-mcp"), then click Create and Continue
  6. You can skip the optional role/access steps — click Done
  7. On the Credentials page, click on the service account you just created
  8. Go to the Keys tab → Add Key → Create new key → select JSON → click Create
  9. A .json key file will download — save it somewhere safe (e.g. ~/.config/gcloud/service-account-key.json)

[!CAUTION] Treat this key file like a secret key. Do not save it inside your project repo or commit it to git. Store it outside your project directory and reference it by absolute path in your MCP config.

Google Search Console access

  1. Copy the service account's email address (it looks like name@project-id.iam.gserviceaccount.com — you can find it on the service account details page)
  2. Go to Google Search Console
  3. Select your property, then go to Settings → Users and permissions
  4. Click Add user, paste the service account email, set the permission to Restricted, and click Add

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "gsc": {
      "command": "node",
      "args": ["/absolute/path/to/google-search-console-mcp/build/index.js"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/service-account-key.json"
      }
    }
  }
}

Claude Code (VS Code)

Add to the "mcpServers" object in ~/.claude.json:

{
  "mcpServers": {
    "gsc": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/google-search-console-mcp/build/index.js"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/service-account-key.json"
      }
    }
  }
}

Usage

Once configured, ask Claude naturally:

  • "List my Search Console properties"
  • "Show me the top 20 queries for my site over the last 28 days"
  • "Check the indexing status of https://example.com/blog/my-post"
  • "Compare mobile vs desktop performance this month"
  • "What sitemaps are submitted for my site?"

License

MIT

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
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
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
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