searchconsole-mcp

searchconsole-mcp

Enables automation of Google Search Console tasks, including retrieving search analytics, managing sitemaps and site properties, and inspecting URLs for index status and crawl information.

Category
访问服务器

README

searchconsole-mcp

MCP server that automates Google Search Console for your projects: search analytics, sitemap management, site properties and URL inspection.

Tools

Tool Description
gsc_list_sites List all properties the service account can access
gsc_add_site / gsc_remove_site Add/remove a property (sc-domain:example.com or https://www.example.com/)
gsc_search_analytics Clicks, impressions, CTR, position grouped by query/page/country/device/date, with filters. Defaults to last 28 days
gsc_list_sitemaps / gsc_get_sitemap Inspect submitted sitemaps and indexed counts
gsc_submit_sitemap / gsc_delete_sitemap Submit or remove sitemaps
gsc_inspect_url URL Inspection API: index status, canonical, crawl info, mobile usability

One-time Google setup

  1. In Google Cloud Console create a project.
  2. Enable the Google Search Console API (APIs & Services > Library).
  3. Create a Service account (IAM & Admin > Service Accounts) and download a JSON key.
  4. For each Search Console property: Settings > Users and permissions > Add user, paste the service account email (...@...iam.gserviceaccount.com) and grant Owner (Owner is required for the URL Inspection API).

Configuration

Environment variables:

Var Required Description
GSC_SERVICE_ACCOUNT_JSON one of Full service-account JSON key inline
GSC_SERVICE_ACCOUNT_FILE one of Path to the key file. Defaults to ./service-account.json
GSC_DEFAULT_SITE optional Default property so you can omit siteUrl per call

The server also loads .env from its working directory at startup.

Register in an MCP client

opencode (~/.config/opencode/opencode.json or project .opencode/opencode.json):

{
  "mcp": {
    "searchconsole": {
      "type": "local",
      "command": ["node", "/absolute/path/to/searchconsole-mcp/dist/index.js"],
      "environment": {
        "GSC_SERVICE_ACCOUNT_FILE": "/absolute/path/to/service-account.json",
        "GSC_DEFAULT_SITE": "sc-domain:example.com"
      }
    }
  }
}

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "searchconsole": {
      "command": "node",
      "args": ["/absolute/path/to/searchconsole-mcp/dist/index.js"],
      "env": {
        "GSC_SERVICE_ACCOUNT_FILE": "/absolute/path/to/service-account.json",
        "GSC_DEFAULT_SITE": "sc-domain:example.com"
      }
    }
  }
}

Development

npm install
npm run build     # tsc -> dist/
npm start         # run the server on stdio
npm run smoke     # boots the server and lists tools

Notes

  • Analytics data lags ~2 days; pass dataState: "all" to include fresh partial data.
  • The API caps analytics rows at 25,000 per request; use startRow to page.
  • Adding a site via API leaves it unverified until ownership is confirmed; easiest path is adding the service account email as an Owner in the UI first.

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