Google Search Console MCP

io.github.surendranb由 GitHub 账号 surendranb 发布v0.10.10更新于 Nov 3, 2026

Google Search Console MCP: search performance analytics, rankings, sitemaps, and indexing health.

已验证STDIO仅桌面网页搜索与抓取数据与分析

概览

AI 生成的概览

本地 MCP 服务器，让助手查询 Google Search Console 搜索表现数据、管理站点地图，并使用 SEO 分析手册。

可以做什么
  • 列出已验证的 Search Console 资源及其权限级别
  • 查询可用维度与指标，再按查询词、页面、国家、设备或日期获取点击、展示、点击率与平均排名
  • 列出、提交和删除该资源的 XML 站点地图
  • 列出并读取内置 SEO 分析手册，获取字段组合与结果解读方法
  • 检查 PyPI 新版本，并交互式修复凭据或资源配置错误
适用场景
适合让助手在不离开对话的情况下拉取并解读自有站点的自然搜索表现、检查站点地图，或按结构化 SEO 手册进行分析。
运行要求
以本地 Python 包运行（uvx 或 npx 包装）。需要 Google Cloud 服务账号 JSON 密钥文件，通过 GOOGLE_APPLICATION_CREDENTIALS 提供绝对路径，并配置站点地址（GSC_SITE_URL）且该账号有权访问该资源。需要访问 Google API 的网络连接。
安装前请注意
服务账号密钥文件可访问你的 Search Console 数据，需妥善保管。提交与删除站点地图的工具会改动线上资源配置。README 说明该包会发送匿名诊断遥测，除非设置 DO_NOT_TRACK 或 MCP_TELEMETRY_OPT_OUT。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Google Search Console MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Google Search Console (GSC) MCP Server 🔍

Model Context Protocol (MCP) server for Google Search Console: search performance analytics, keyword rankings, sitemap inspection, and indexing health for AI agents.

[CI] [PyPI version] [npm version] [OpenSSF Scorecard] [License: MIT]

🌐 Live Documentation & Web Portal: https://gsc.builditwithai.xyz

⚡ Quickstart

bash
# 1-Line Universal Installer (Auto-configures Claude Desktop, Cursor, Claude Code, Antigravity, VS Code, Zed, Windsurf)curl -fsSL "https://gsc.builditwithai.xyz/install" | bash
# Or run directly via your preferred runtime:uvx google-search-console-mcpnpx -y @surendranb/google-search-console-mcp

🤖 Client Setup

A. Claude Code (CLI)

bash
claude mcp add google-search-console -- uvx google-search-console-mcp

B. Cursor & Google Antigravity (mcp.json)

json
{  "mcpServers": {    "google-search-console": {      "command": "uvx",      "args": ["google-search-console-mcp"]    }  }}

C. Claude Desktop (claude_desktop_config.json)

json
{  "mcpServers": {    "google-search-console": {      "command": "uvx",      "args": ["google-search-console-mcp"],      "env": {        "GSC_SITE_URL": "https://example.com/",        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service_account.json"      }    }  }}

D. VS Code (Cline / Roo Code / Continue)

json
{  "mcpServers": {    "google-search-console": {      "command": "npx",      "args": ["-y", "@surendranb/google-search-console-mcp"]    }  }}

🛠️ Tools & Capabilities

Tool NameParametersDescriptionReturn Type
get_search_analyticssite_url (string), start_date (string), end_date (string), dimensions (list), row_limit (int)Queries organic search clicks, impressions, CTR, and average position grouped by query, page, country, device, and date.JSON / Markdown
list_sites(none)Lists all verified web properties in Google Search Console with permission levels.JSON
inspect_urlsite_url (string), inspection_url (string)Real-time URL inspection for index status, crawl issues, canonicalization, and mobile usability.JSON
list_sitemapssite_url (string)Retrieves all submitted XML sitemaps, last download date, and indexed URL counts.JSON
submit_sitemapsite_url (string), feedpath (string)Submits a new XML sitemap directly to Google Search Console.JSON
delete_sitemapsite_url (string), feedpath (string)Removes an obsolete or incorrect sitemap from Search Console.JSON
skill_readskill_name (string)Loads expert SEO diagnostic playbooks dynamically from GitHub.Markdown
skills_list(none)Lists all available live GSC analytical skills.JSON

🔒 Telemetry & Privacy

This package collects anonymous, non-PII diagnostic telemetry (command executions, latency, error codes) to improve tool reliability. No queries, user credentials, personal data, source code, or environment variables are ever collected or stored.

You can opt out anytime by setting either of the following environment variables:

bash
export DO_NOT_TRACK=1# orexport MCP_TELEMETRY_OPT_OUT=1

📄 License

MIT License. See LICENSE for details.

来源：README.md，提交 96dfd0b

工具

12

list_gsc_sites

List all sites verified in Google Search Console. Returns: List of verified sites with their permission levels.

无需输入参数。

list_sites

List all sites verified in Google Search Console (alias for list_gsc_sites). Returns: List of verified sites with their permission levels.

无需输入参数。

list_available_dimensions

List all available GSC dimensions with their descriptions. Returns: List of dimension objects with api_name and description.

无需输入参数。

list_available_metrics

List all available GSC metrics with their descriptions. Returns: List of metric objects with api_name and description.

无需输入参数。

skills_list

List available analytical skills (playbooks) for Google Search Console. Use this to learn proven field combinations and how to interpret GSC data for specific SEO tasks. Fetch the full playbook with skill_read.

无需输入参数。

skill_read

Fetch the full content of one analytical skill (playbook) for Google Search Console. Args: skill_id: The skill id from skills_list (e.g., "brand_visibility.md") Returns: The full skill content with title, description, and playbook steps.

输入参数skill_id必填

get_search_analytics

Retrieve Google Search Console search analytics data. Args: dimensions: List of dimensions from: country, device, page, query, searchAppearance, date start_date: Start date in YYYY-MM-DD format (defaults to 30 days ago) end_date: End date in YYYY-MM-DD format (defaults to 3 days ago) filters: List of filter objects (e.g., [{"dimension": "country", "operator": "equals", "expression": "usa"}]) search_type: Type of search ('web', 'image', 'video', 'news', 'discover', 'googleNews') row_limit: Maximum number of rows to return (max 25000) start_row: Starting row for pagination (0-based) summary_only: If True, returns only aggregated totals (Token Efficient) intent: Short plain-English description of what the user is trying to learn/accomplish. E.g. "which queries drive clicks to the pricing page", "mobile vs desktop performance last month". Returns: Dictionary containing search analytics data with clicks, impressions, ctr, and position metrics.

输入参数intentfiltersend_daterow_limitstart_rowdimensionsstart_datesearch_typesummary_only

get_sitemaps

Get all sitemaps for the configured site. Returns: List of sitemaps with their status and details.

无需输入参数。

submit_sitemap

Submit a sitemap to Google Search Console. Args: sitemap_url: Full URL of the sitemap to submit Returns: Success message or error details.

输入参数sitemap_url必填

delete_sitemap

Delete a sitemap from Google Search Console. Args: sitemap_url: Full URL of the sitemap to delete Returns: Success message or error details.

输入参数sitemap_url必填

check_for_updates

Check PyPI for newer versions of this MCP server and get upgrade instructions.

无需输入参数。

setup_gsc_access

Interactively fix a broken Google Search Console MCP setup (missing or wrong credentials path, missing GSC_SITE_URL, invalid key, or missing property access) by asking the user for the needed value through the client, then re-initializing without a restart. Call this whenever a configuration or authentication error is reported.

无需输入参数。

版本历史

1
  1. v0.10.10最新Oct 29, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分