GSC-MCP-Server
Connects Google Search Console to MCP clients to query search analytics, manage sitemaps, and perform URL inspections. It enables users to identify SEO opportunities and generate performance reports through natural language interactions.
README
GSC-MCP-Server
Google Search Console MCP Server β Connect Google Search Console to Claude, Cursor, and other MCP clients.
Features
- π Search Analytics β Query clicks, impressions, CTR, and position data
- π SEO Opportunities β Find low-CTR keywords, detect cannibalization issues
- π Reports β Weekly summaries, period comparisons
- πΊοΈ Sitemaps β List, submit, and manage sitemaps
- π URL Inspection β Check indexing status (requires full scope)
- πΎ Caching β SQLite cache for faster repeated queries
- π Secure β OAuth tokens stored in OS keychain
Quick Start
# Install globally
npm install -g @appsyogi/gsc-mcp-server
# Set up OAuth credentials
gsc-mcp init
# Verify setup
gsc-mcp doctor
# Start the server (for MCP clients)
gsc-mcp run
Prerequisites
1. Create Google Cloud OAuth Credentials
You need to create your own OAuth credentials in Google Cloud Console:
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Search Console API:
- Go to "APIs & Services" β "Library"
- Search for "Google Search Console API"
- Click "Enable"
- Create OAuth credentials:
- Go to "APIs & Services" β "Credentials"
- Click "Create Credentials" β "OAuth client ID"
- Choose "Desktop application"
- Name it (e.g., "GSC-MCP")
- Click "Create"
- Copy the Client ID and Client Secret
- Add test users (required while app is in testing mode):
- Go to "APIs & Services" β "OAuth consent screen"
- Scroll to "Test users" section
- Click "Add users"
- Add the Google account email(s) you'll use to authenticate
- Click "Save"
Note: While your app's publishing status is "Testing", only test users can authenticate. You can add up to 100 test users.
2. Configure GSC-MCP
Run the init command and enter your credentials:
gsc-mcp init
This will:
- Prompt for your Client ID and Client Secret
- Open a browser for Google authentication
- Store your refresh token securely in the OS keychain
Usage
CLI Commands
# Initialize with OAuth (interactive)
gsc-mcp init
# Initialize with service account
gsc-mcp init --service-account /path/to/key.json
# Initialize with full scope (for sitemap submission, URL inspection)
gsc-mcp init --scope full
# Check configuration and connectivity
gsc-mcp doctor
gsc-mcp doctor --verbose
# Start MCP server (stdio mode)
gsc-mcp run
# Start in HTTP mode (for debugging)
gsc-mcp run --http 3333
# View current configuration
gsc-mcp config
# Clear credentials
gsc-mcp logout
MCP Client Configuration
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"gsc": {
"command": "gsc-mcp",
"args": ["run"]
}
}
}
VS Code (Copilot)
Add to your VS Code MCP settings (~/.vscode/mcp.json or workspace settings):
{
"servers": {
"gsc": {
"command": "gsc-mcp",
"args": ["run"],
"type": "stdio"
}
}
}
Cursor
Add to your Cursor MCP config:
{
"mcpServers": {
"gsc": {
"command": "npx",
"args": ["-y", "@appsyogi/gsc-mcp-server", "run"]
}
}
}
Available Tools
Search Analytics
| Tool | Description |
|---|---|
searchanalytics.query |
Query search performance data with dimensions and filters |
report.comparePeriods |
Compare two time periods |
Sitemaps
| Tool | Description | Scope |
|---|---|---|
sitemaps.list |
List all sitemaps | readonly |
sitemaps.get |
Get sitemap details | readonly |
sitemaps.submit |
Submit a sitemap | full |
sitemaps.delete |
Delete a sitemap | full |
URL Inspection
| Tool | Description | Scope |
|---|---|---|
urlInspection.inspect |
Inspect a URL's indexing status | full |
urlInspection.batchInspect |
Inspect multiple URLs | full |
SEO Opportunities
| Tool | Description |
|---|---|
opportunities.lowCtrHighPos |
Find quick-win keywords (position 4-20, low CTR) |
opportunities.cannibalization |
Detect keyword cannibalization |
report.weeklySummary |
Generate weekly performance summary |
Export
| Tool | Description |
|---|---|
export.csv |
Export data as CSV |
export.json |
Export data as JSON |
Resources
The server exposes browsable resources:
gsc://sitesβ List all propertiesgsc://sites/{siteUrl}/sitemapsβ List sitemaps for a property
Scopes
GSC-MCP supports two permission levels:
Readonly (default)
- Search analytics queries
- List sitemaps
- SEO analysis tools
gsc-mcp init # Uses readonly by default
Full
- Everything in readonly, plus:
- Submit/delete sitemaps
- URL inspection
gsc-mcp init --scope full
Configuration Files
GSC-MCP stores configuration in platform-specific locations:
| Platform | Config Path |
|---|---|
| macOS | ~/.config/gsc-mcp/ |
| Linux | ~/.config/gsc-mcp/ |
| Windows | %APPDATA%/gsc-mcp/ |
Files:
config.jsonβ OAuth client ID/secret, scope settingscache.sqliteβ Query cache and saved presets
Tokens are stored securely in the OS keychain when available.
Service Account Setup
For automated/server use, you can use a service account instead of OAuth:
- Create a service account in Google Cloud Console
- Download the JSON key file
- Add the service account email as an owner in Google Search Console
- Initialize:
gsc-mcp init --service-account /path/to/key.json
API Quotas
Google Search Console API has a default quota of 1,200 queries per day. GSC-MCP includes:
- Automatic retry with exponential backoff
- Query caching to reduce API calls
- Pagination handling for large result sets
Examples
Find Quick-Win Keywords
Use gsc-mcp to find quick-win opportunities for my site https://example.com
Weekly Report
Generate a weekly performance summary for https://example.com
Compare Periods
Compare search performance for https://example.com between last week and the week before
Export Data
Export the top 1000 queries for https://example.com in the last 28 days as CSV
Development
# Clone the repo
git clone https://github.com/AppsYogi-com/gsc-mcp-server.git
cd gsc-mcp-server
# Install dependencies
npm install
# Build
npm run build
# Run in dev mode
npm run dev
# Test locally
node dist/cli/index.js doctor
License
MIT
Contributing
Contributions are welcome! Please open an issue or PR.
Credits
Built with:
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.