Google Search Console MCP Server

Google Search Console MCP Server

Enables querying Google Search Console data including rankings, clicks, and impressions for websites. Provides tools for analyzing search performance, top queries, page metrics, and ranking changes.

Category
访问服务器

README

Google Search Console MCP Server

Query Google Search Console data from any AI assistant that supports the MCP protocol - rankings, clicks, impressions, and page-level performance.

Prerequisites

  • Node.js 18+
  • A Google account with access to Google Search Console

Setup

1. Install dependencies

npm install

2. Create a Google Cloud project

  1. Go to Google Cloud Console
  2. Create a new project (or select an existing one)
  3. Enable the Search Console API:
    • Go to APIs & Services > Library
    • Search for "Search Console API"
    • Click Enable

3. Create OAuth2 credentials

  1. Go to APIs & Services > Credentials
  2. Click Create Credentials > OAuth client ID
  3. Application type: Desktop app (or Web application)
  4. Name it whatever you like
  5. Copy the Client ID and Client Secret

4. Configure your .env file

cp .env.example .env

Fill in the values:

Variable Where to find it
GSC_SITE_URL GSC Settings > Association > Sc-domain (e.g. sc-domain:bwengr.com)
GOOGLE_CLIENT_ID Google Cloud Console > Credentials (from step 3)
GOOGLE_CLIENT_SECRET Google Cloud Console > Credentials (from step 3)

5. Run the server

npm start

On first run, a browser window will open automatically to complete OAuth authentication. After that, tokens are stored locally in .tokens.json and you will not be prompted again.

Connecting to your AI assistant

This server communicates over stdio (standard input/output), which is the standard way to connect MCP servers to AI assistants. Configure your AI assistant to use:

node /path/to/src/index.js

Replace /path/to with the actual path to this project on your machine.

Available tools

getTopQueries

Returns your top search queries ranked by clicks.

  • Parameters: startDate (YYYY-MM-DD), endDate (YYYY-MM-DD), rowLimit (optional, default 10)
  • Returns: query, clicks, impressions, CTR, position for each row

getSiteSummary

Returns overall site search performance totals.

  • Parameters: startDate (YYYY-MM-DD), endDate (YYYY-MM-DD)
  • Returns: total clicks, impressions, CTR, average position

getPagePerformance

Returns performance data filtered to a specific page.

  • Parameters: pageUrl (exact URL as shown in GSC), startDate (YYYY-MM-DD), endDate (YYYY-MM-DD)
  • Returns: clicks, impressions, CTR, position for that page

getRankingChanges

Finds pages with the biggest position changes between two periods.

  • Parameters: days (number of days to compare, default 28)
  • Returns: page URL, position change, current position, prior position

Important

Never commit .env or .tokens.json to version control. These files are already excluded via .gitignore.

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