gsc-mcp-server
Enables Claude to access Google Search Console data including search performance, URL indexation, sitemaps, and built-in SEO analysis tools such as trending queries, cannibalization detection, and traffic drop diagnostics.
README
Google Search Console MCP Server
An MCP server that gives Claude direct access to your Google Search Console data — search performance, URL indexation, sitemaps, and built-in SEO analysis tools including trending queries, cannibalization detection, traffic drop diagnostics, and automated query/page grouping.
Prerequisites
- Node.js >= 18.0.0
- A C++ compiler (required by the
better-sqlite3dependency):
| Platform | Install |
|---|---|
| macOS | xcode-select --install |
| Windows | Visual Studio Build Tools — select "Desktop development with C++" |
| Linux (Debian/Ubuntu) | sudo apt-get install build-essential python3 |
| Linux (Fedora/RHEL) | sudo dnf groupinstall "Development Tools" && sudo dnf install python3 |
Quick Start
git clone https://github.com/serpfire/gsc-mcp-server.git
cd gsc-mcp-server
npm install
1. Create Google OAuth credentials
- Go to Google Cloud Console
- Create an OAuth 2.0 Client ID (type: Desktop app)
- Enable the Google Search Console API in your project
2. Authenticate
GSC_OAUTH_CLIENT_ID=your-client-id \
GSC_OAUTH_CLIENT_SECRET=your-client-secret \
npm run setup
This opens your browser to sign in with Google. Tokens are stored at ~/.gsc-mcp/tokens.json and auto-refresh. Run setup again anytime to switch accounts.
3. Add to Claude Code
claude mcp add --transport stdio gsc -s user \
-e GSC_OAUTH_CLIENT_ID=your-client-id \
-e GSC_OAUTH_CLIENT_SECRET=your-client-secret \
-- node /absolute/path/to/gsc-mcp-server/src/index.js
Or manually add to ~/.claude.json:
{
"mcpServers": {
"gsc": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/gsc-mcp-server/src/index.js"],
"env": {
"GSC_OAUTH_CLIENT_ID": "your-client-id",
"GSC_OAUTH_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Service Account Alternative
For automation or server-to-server use:
{
"env": {
"GSC_AUTH_MODE": "service_account",
"GSC_SERVICE_ACCOUNT_KEY_PATH": "/path/to/key.json"
}
}
Tools
Core GSC Tools
| Tool | Description |
|---|---|
list_sites |
List all verified GSC properties |
get_site |
Get details for a specific site |
query_search_analytics |
Query clicks, impressions, CTR, position with dimensions/filters/pagination |
inspect_url |
Check URL index/crawl status (2,000/day limit) |
list_sitemaps |
List sitemaps for a site |
get_sitemap |
Get sitemap details |
submit_sitemap |
Submit a new sitemap |
delete_sitemap |
Remove a sitemap from GSC |
switch_account |
Re-authenticate with a different Google account (OAuth only) |
Data Sync
| Tool | Description |
|---|---|
sync_search_data |
Fetch all performance data into local SQLite cache. Incremental by default. Required before analysis tools. |
Analysis Tools
| Tool | Description |
|---|---|
find_low_hanging_fruit |
Find queries ranking 2-20 with high impressions but low CTR, scored by untapped potential |
detect_cannibalization |
Detect queries ranking on 2+ URLs using HHI scoring with action recommendations |
find_trending_queries |
Find queries with biggest growth/decline (period-over-period or year-over-year) |
find_trending_pages |
Find pages with biggest growth/decline with impact scoring |
analyze_traffic_drop |
Diagnose traffic drops across 5 views: site-level, GBP vs organic, groups, segments, brand vs non-brand |
get_group_performance |
Aggregated metrics broken down by named groups with share percentages |
Group Management
| Tool | Description |
|---|---|
create_group |
Create a group with OR/AND/NOT regex rules for URL segments or query groups |
list_groups |
List all groups, optionally filtered by dimension |
get_group |
Get group details including rules |
update_group |
Update group description and/or rules |
delete_group |
Delete a group and its rules |
test_group |
Test a group against cached data — match count, rate, samples |
Auto-Discovery
| Tool | Description |
|---|---|
discover_query_groups |
Auto-cluster queries using word overlap, n-gram similarity, and page co-occurrence |
promote_cluster_to_group |
Convert a discovered cluster into a named group |
auto_segment_pages |
Auto-create URL segment groups from page URL patterns |
auto_group_queries |
Auto-create query groups: brand, topic n-grams, intent modifiers |
Resources
| URI | Description |
|---|---|
sites://list |
All verified sites (auto-discovery) |
Prompts
| Name | Description |
|---|---|
seo_performance_analysis |
Guided full SEO review (queries, pages, devices, trends) |
index_coverage_check |
Systematic URL indexation report |
Example Queries
- "List my Search Console sites"
- "Show top 20 queries for sc-domain:example.com last 7 days"
- "Compare mobile vs desktop for https://example.com/"
- "Check if https://example.com/new-page is indexed"
- "Show sitemaps for sc-domain:example.com"
- "Sync data for sc-domain:example.com and find low-hanging fruit"
- "Detect keyword cannibalization on sc-domain:example.com"
- "Show trending queries for sc-domain:example.com last 28 days"
- "Auto-create query groups for sc-domain:example.com"
Architecture
src/
├── index.js # Entry: auth -> client -> db -> server -> stdio
├── server.js # McpServer factory
├── auth/
│ ├── index.js # Auth factory (auto-detects mode from env)
│ ├── service-account.js # Service account key file auth
│ ├── oauth.js # Browser flow + token persistence + auto-recovery
│ ├── token-store.js # ~/.gsc-mcp/tokens.json
│ └── setup.js # Standalone setup script
├── gsc/ # Pure GSC API wrappers (no MCP knowledge)
│ ├── client.js
│ ├── sites.js
│ ├── search-analytics.js
│ ├── sitemaps.js
│ └── url-inspection.js
├── db/
│ ├── connection.js # SQLite setup with WAL mode
│ └── schema.js # Migrations
├── analysis/ # SEO analysis engine (uses local SQLite)
│ ├── sync.js # GSC API -> SQLite incremental sync
│ ├── low-hanging-fruit.js # Opportunity scoring
│ ├── cannibalization.js # HHI-based detection
│ ├── trending.js # PoP / YoY trending queries & pages
│ ├── traffic-drop.js # Multi-view drop diagnostics
│ ├── group-performance.js # Group-level aggregation
│ ├── auto-segment.js # Automatic URL segmentation
│ ├── auto-group.js # Automatic query grouping
│ ├── shared.js # Shared SQL helpers
│ ├── groups/
│ │ ├── manager.js # CRUD for groups + rules
│ │ ├── compiler.js # OR/AND/NOT rule compilation
│ │ └── matcher.js # Regex matching engine
│ └── semantic/
│ ├── discover.js # Cluster discovery orchestrator
│ ├── clustering.js # Connected components algorithm
│ ├── similarity.js # Multi-signal similarity scoring
│ └── labeler.js # Cluster naming
├── tools/
│ ├── definitions.js # Core GSC tools (declarative)
│ ├── analysis-definitions.js # Analysis tools (declarative)
│ ├── middleware.js # Rate limiting + error handling wrapper
│ ├── auth.js # switch_account tool
│ └── index.js # Registration loop
├── resources.js # sites://list resource
├── prompts.js # SEO analysis + index check prompts
└── utils/
├── logger.js # stderr-only (stdout = MCP protocol)
├── errors.js # Google API error -> MCP error
├── constants.js # Scopes, rate limits, defaults
├── rate-limiter.js # Sliding window
└── open-url.js # Cross-platform browser opener
Two-layer separation: gsc/ knows nothing about MCP. tools/ knows nothing about Google's API. analysis/ operates on local SQLite data. Each layer is independently testable.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GSC_AUTH_MODE |
No | Auto-detected | oauth or service_account. Auto-detected from which credentials are set. |
GSC_OAUTH_CLIENT_ID |
OAuth | — | OAuth client ID |
GSC_OAUTH_CLIENT_SECRET |
OAuth | — | OAuth client secret |
GSC_OAUTH_REFRESH_TOKEN |
No | — | Skip browser flow with a pre-existing token |
GSC_SERVICE_ACCOUNT_KEY_PATH |
Service acct | — | Path to JSON key file |
GSC_API_SCOPES |
No | webmasters.readonly |
Override scopes (comma-separated) |
GSC_LOG_LEVEL |
No | info |
debug / info / warn / error |
GSC_TOKEN_PATH |
No | ~/.gsc-mcp/tokens.json |
Custom token storage path |
GSC_DB_PATH |
No | ~/.gsc-mcp/data.db |
Custom SQLite database path |
Debugging
Launch the MCP Inspector for interactive testing:
npm run inspect
Windows note: The inspect script uses bash. Run it from Git Bash, WSL, or replace with:
npx @modelcontextprotocol/inspector node src/index.js
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。