gsc-mcp-rs
MCP server for Google Search Console. 21 tools for search analytics, keyword opportunities, URL inspection, sitemaps, indexing, and property management.
README
gsc-mcp-rs
A fast, single-binary MCP server for Google Search Console. 21 tools covering search analytics, URL inspection, sitemaps, indexing, and property management.
Features
- 21 tools across 9 groups: analytics, discovery, inspection, sitemaps, indexing, properties, meta
- Both auth methods: OAuth 2.0 (personal) and Service Account (automation)
- Error-as-UI: operational errors return guidance text, never crash the conversation
- Zero runtime deps: single Rust binary, no Node/Python/Java required
- sc-domain: support: domain properties work correctly from day one
Quick Start
Install
cargo install gsc-mcp-rs
Or build from source:
git clone https://github.com/eyupcanakman/gsc-mcp-rs.git
cd gsc-mcp-rs
cargo build --release
Configure Auth
Option 1: OAuth (personal use)
- Go to Google Cloud Console > APIs & Services > Credentials
- Create an OAuth 2.0 Client ID (Desktop app type)
- Enable the Search Console API and Indexing API
- Save credentials:
mkdir -p ~/.config/gsc-mcp-rs
cat > ~/.config/gsc-mcp-rs/oauth_credentials.json << 'EOF'
{"client_id": "YOUR_CLIENT_ID", "client_secret": "YOUR_CLIENT_SECRET"}
EOF
- Authenticate (opens browser, completes via localhost callback):
gsc-mcp-rs auth
Option 2: Service Account (automation)
- Create a service account in Google Cloud Console
- Grant it access to your Search Console properties (Full permission)
- Download the JSON key and place it:
cp your-key.json ~/.config/gsc-mcp-rs/service_account.json
Or set the environment variable:
export GSC_SERVICE_ACCOUNT_PATH=/path/to/key.json
Add to Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"gsc": {
"command": "gsc-mcp-rs",
"args": ["stdio"]
}
}
}
Add to Claude Code
claude mcp add gsc-mcp-rs -- gsc-mcp-rs stdio
Tools (21)
Properties & Auth
| Tool | Description |
|---|---|
list_sites |
List all accessible GSC properties with permission levels |
get_site_details |
Get verification status and ownership details |
manage_site |
Add or remove a property (action: "add"|"delete", idempotent) |
reauthenticate |
Clear tokens for account switching |
Search Analytics
| Tool | Description |
|---|---|
search_analytics |
All dimensions, filters, 25K rows, sorting. Use breakdown for device/country splits |
compare_periods |
Side-by-side period comparison with deltas |
performance_overview |
Quick aggregate summary + daily trend |
page_query_breakdown |
Which queries drive traffic to a specific page |
Discovery & Analysis
| Tool | Description |
|---|---|
top_pages |
Best-performing pages by clicks/impressions/CTR/position |
keyword_opportunities |
5 modes: quick_wins (default), cannibalization, ctr_gaps, declining, growing |
brand_query_analysis |
Brand vs non-brand traffic split |
keyword_trend |
Daily tracking of a single keyword |
detect_anomalies |
Automatic drop detection with severity levels |
Search Appearance
| Tool | Description |
|---|---|
query_by_search_appearance |
Filter by rich result type (FAQ, VIDEO, etc.) |
Export
| Tool | Description |
|---|---|
export_analytics |
Force CSV file export for large datasets |
URL Inspection
| Tool | Description |
|---|---|
inspect_url |
Check indexing status of a single URL |
batch_inspect_urls |
Inspect up to 50 URLs with configurable concurrency |
Sitemaps
| Tool | Description |
|---|---|
list_sitemaps |
List submitted sitemaps with status |
manage_sitemap |
Submit or remove a sitemap (action: "submit"|"delete", idempotent) |
Indexing API
| Tool | Description |
|---|---|
request_indexing |
Request Google to crawl a URL |
Meta
| Tool | Description |
|---|---|
api_reference |
All dimensions and metrics with descriptions and value ranges |
Environment Variables
| Variable | Default | Description |
|---|---|---|
GSC_MCP_CONFIG_DIR |
~/.config/gsc-mcp-rs/ |
Config and token storage directory |
GSC_MCP_OUTPUT_DIR |
System temp dir | CSV export directory |
GSC_SERVICE_ACCOUNT_PATH |
(none) | Path to service account JSON key |
CLI Usage
gsc-mcp-rs stdio # stdio transport (default)
gsc-mcp-rs auth # Interactive OAuth flow
gsc-mcp-rs --version # Show version
gsc-mcp-rs --help # Show help
Docker
docker build -t gsc-mcp-rs .
docker run -i --rm -v ~/.config/gsc-mcp-rs:/root/.config/gsc-mcp-rs gsc-mcp-rs
Minimum Supported Rust Version (MSRV)
Rust 1.85 or later.
Contributing
See CONTRIBUTING.md for development setup and guidelines.
Security
See SECURITY.md for the vulnerability reporting process.
License
MIT. See LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.