mcp-gsc
MCP server for Google Search Console, enabling querying search analytics, URL inspection, sitemap management, and more via natural language.
README
<p align="center"> <img src="logo.svg" alt="mcp-gsc" width="280" /> </p>
<h1 align="center">mcp-gsc</h1>
<p align="center"> Google Search Console MCP server — query search analytics, inspect URLs, manage sitemaps & more via natural language. <br/> Built with Bun + TypeScript. Works with Claude, Cursor, and any MCP client. </p>
Quick Start
1. Get Credentials
You need OAuth client credentials from Google Cloud Console.
-
Go to Google Cloud Console
-
Create a project (or select existing)
-
Enable the Google Search Console API:
- APIs & Services → Library → search "Google Search Console API" → Enable
-
Configure OAuth consent screen (if not done):
- APIs & Services → OAuth consent screen → External
- Fill in app name + your email, add scope
https://www.googleapis.com/auth/webmasters
-
Create credentials:
- APIs & Services → Credentials → Create Credentials → OAuth client ID
- Application type: Desktop app (allows localhost redirects automatically)
- Download the JSON file
-
Set the credentials path:
export GOOGLE_GSC_CREDENTIALS_PATH=/path/to/credentials.json
- Run setup to authorize:
npx mcp-gsc setup
This opens your browser for OAuth consent, saves a refresh token, verifies access to your GSC properties, and prints config snippets for your MCP client.
2. Add to Claude Code
claude mcp add gsc --scope user --transport stdio \
-e GOOGLE_GSC_CREDENTIALS_PATH=/path/to/credentials.json \
-- npx -y mcp-gsc@latest
That's it. Restart Claude Code and the tools are available.
Also works with
bunx mcp-gsc@latestif you have Bun. Requires Node 18+ when running vianpx.
Claude Desktop / Cursor
Add to your claude_desktop_config.json:
{
"mcpServers": {
"gsc": {
"command": "npx",
"args": ["-y", "mcp-gsc@latest"],
"env": {
"GOOGLE_GSC_CREDENTIALS_PATH": "/path/to/credentials.json"
}
}
}
}
Codex CLI
Add to ~/.codex/config.toml (TOML, not JSON):
[mcp_servers.gsc]
command = "npx"
args = ["-y", "mcp-gsc@latest"]
startup_timeout_sec = 30
env = { GOOGLE_GSC_CREDENTIALS_PATH = "/path/to/credentials.json" }
Codex defaults to a 10s startup timeout, which is often too short for a cold
npxfetch. Bumpstartup_timeout_sec(30 is safe) or install the package globally (npm i -g mcp-gsc) and usecommand = "mcp-gsc"instead.
Service Account (alternative)
For server-to-server auth without browser-based OAuth:
- Create a service account in Google Cloud Console
- Download the JSON key file
- In Google Search Console, add the service account email as a user for each property
- Point
GOOGLE_GSC_CREDENTIALS_PATHto the key file — auth type is auto-detected
Tools (25)
Core Tools (always available)
Sites
| Tool | Description |
|---|---|
list_properties |
List all GSC properties with permission levels |
get_property_details |
Verification info, ownership, permissions for a property |
Search Analytics
| Tool | Description |
|---|---|
search_analytics |
Query search performance (clicks, impressions, CTR, position) with dimensions, filters, and brand segmentation |
Dimensions: query, page, country, device, date, searchAppearance, hour
Types: web, image, video, news, discover, googleNews
Note: searchAppearance cannot combine with query or page. hour requires data_state="hourly_all" (last 10 days only). Country codes are ISO 3166-1 alpha-3 (usa, gbr, deu).
Sitemaps
| Tool | Description |
|---|---|
list_sitemaps |
List sitemaps with status, type, indexed counts, errors |
get_sitemap |
Detailed sitemap info with content breakdown |
URL Inspection
| Tool | Description |
|---|---|
inspect_url |
URL indexing status, crawl info, rich results, canonicals |
batch_inspect_urls |
Inspect up to 10 URLs at once with categorized results |
Rate limits: 600/minute + 2,000/day per site (tracked automatically).
Export
| Tool | Description |
|---|---|
export_csv |
Export full search analytics to CSV file (auto-paginates, up to 25K rows) |
Extended Tools (disabled by default)
Enable with GOOGLE_GSC_ENABLE_EXTENDED_TOOLS=true:
Reporting Suite
| Tool | Description |
|---|---|
performance_overview |
Aggregate metrics + daily trend breakdown |
compare_periods |
Compare two date ranges with delta calculations |
top_movers |
Biggest gains and drops between periods |
device_country_breakdown |
Performance by device and/or country |
SEO Suite
| Tool | Description |
|---|---|
quick_wins |
High-impression, low-CTR queries in striking distance (position 4-20) |
cannibalization |
Multiple pages competing for the same query |
opportunity_finder |
Emerging queries, growing impressions with low CTR, declining performers |
position_tracking |
Position changes over time for specific queries/pages |
ctr_anomalies |
Queries with abnormal CTR relative to position |
content_decay |
Pages/queries with impressions dropping >50% from historical peak |
weekly_seo_report |
All-in-one report: overview + quick wins + top movers |
Technical SEO Suite
| Tool | Description |
|---|---|
indexing_coverage |
Batch URL inspection with categorized indexing status |
sitemap_health |
Sitemap error patterns, freshness, indexed vs submitted ratio |
Write Tools (disabled by default)
Enable with GOOGLE_GSC_ENABLE_WRITES=true:
| Tool | Description |
|---|---|
add_site |
Add a new site to GSC |
delete_site |
Remove a site from GSC |
submit_sitemap |
Submit a new sitemap |
delete_sitemap |
Remove/unsubmit a sitemap |
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
GOOGLE_GSC_CREDENTIALS_PATH |
Yes | — | Path to OAuth client JSON or service account key |
GOOGLE_GSC_TOKEN_PATH |
No | Derived | Path to cached OAuth token (default: *_token.json next to credentials) |
GOOGLE_GSC_PROPERTY |
No | — | Default property URL (e.g., sc-domain:example.com). Accepts bare domains. |
GOOGLE_GSC_ENABLE_WRITES |
No | false |
Enable write tools |
GOOGLE_GSC_ENABLE_EXTENDED_TOOLS |
No | false |
Enable extended analytics tools (13 extra) |
GOOGLE_GSC_ENV_FILE |
No | .env |
Path to .env file |
DEBUG |
No | — | Enable debug logging |
Property resolution: You can pass bare domains like example.com — the server auto-resolves to sc-domain:example.com or https://example.com/ by matching against your verified properties.
Examples
Ask your AI assistant:
- "Show me my top 10 queries this month"
- "Find quick wins for example.com"
- "Which pages have declining traffic over the last 3 months?"
- "Check if these URLs are indexed: url1, url2, url3"
- "Compare this week's performance to last week"
- "Export all search analytics data to CSV for the last 28 days"
- "Run a weekly SEO report for my site"
- "Find keyword cannibalization issues"
Future Tool Ideas
- Content gap analysis (requires competitor data integration)
- Core Web Vitals integration (via PageSpeed Insights API)
- Multi-property comparison
- Search appearance deep analysis
- Integration with Google Analytics for conversion data
- Automated reporting schedules
Updates
Using npx @latest (recommended): You always get the latest version.
Using a binary: The server checks for new releases on startup and logs to stderr if outdated.
mcp-gsc --version
Development
Requires Bun.
git clone https://github.com/pijusz/mcp-gsc.git
cd mcp-gsc
bun install
bun test # tests
bun run build # standalone binary
bun run inspect # MCP Inspector
bun run check # biome format + lint
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。