mcp-gsc-multi-account
Enables managing multiple Google Search Console accounts through a single MCP server, providing tools for search analytics, quick win detection, period comparison, URL inspection and indexing, and sitemap management.
README
MCP GSC Multi-Account
A Model Context Protocol (MCP) server for Google Search Console with multi-account support.
Manage multiple GSC accounts from a single MCP server. Perfect for agencies, SEO professionals, or anyone managing multiple properties.
Features
- π Multi-Account - Switch between accounts dynamically
- π Search Analytics - Up to 25,000 rows with regex filtering
- π― Quick Wins Detection - Automatic SEO opportunity identification
- π Period Comparison - Compare performance between time periods
- π URL Inspection - Check indexing status of any URL
- π€ URL Indexing - Submit URLs for indexing via Indexing API
- πΊοΈ Sitemap Management - List and submit sitemaps
Installation
npm install mcp-gsc-multi-account
Or run directly:
npx mcp-gsc-multi-account
Configuration
Required Environment Variables
GOOGLE_CLIENT_ID=your-client-id.apps.googleusercontent.com
GOOGLE_CLIENT_SECRET=your-client-secret
Account Configuration
Option 1: Single Account (Simple)
GSC_REFRESH_TOKEN=1//your-refresh-token
GSC_EMAIL=user@gmail.com # optional, defaults to "default"
Option 2: Multiple Accounts via JSON
GSC_ACCOUNTS_JSON='{"accounts":[{"id":"main","email":"main@gmail.com","refreshToken":"1//..."},{"id":"client1","email":"client@gmail.com","refreshToken":"1//..."}]}'
Option 3: Multiple Accounts via File
GSC_ACCOUNTS_FILE=/path/to/accounts.json
accounts.json format:
{
"accounts": [
{
"id": "main",
"email": "main@gmail.com",
"refreshToken": "1//..."
},
{
"id": "client1",
"email": "client@gmail.com",
"refreshToken": "1//..."
}
]
}
Option 4: Runtime Registration
Use the register_account tool to add accounts at runtime:
{
"tool": "register_account",
"arguments": {
"id": "newclient",
"email": "newclient@gmail.com",
"refreshToken": "1//..."
}
}
MCP Configuration
Claude Desktop / Cursor
{
"mcpServers": {
"gsc": {
"command": "npx",
"args": ["-y", "mcp-gsc-multi-account"],
"env": {
"GOOGLE_CLIENT_ID": "your-client-id",
"GOOGLE_CLIENT_SECRET": "your-secret",
"GSC_ACCOUNTS_FILE": "/path/to/accounts.json"
}
}
}
}
mcporter
{
"mcpServers": {
"gsc": {
"command": "npx -y mcp-gsc-multi-account",
"env": {
"GOOGLE_CLIENT_ID": "your-client-id",
"GOOGLE_CLIENT_SECRET": "your-secret",
"GSC_REFRESH_TOKEN": "1//your-token"
}
}
}
}
Available Tools
Account Management
register_account
Register a new account at runtime.
id(required): Unique identifieremail(required): Google account emailrefreshToken(required): OAuth2 refresh token
list_accounts
List all registered accounts.
list_sites
List all sites accessible by an account.
account(optional): Account ID or email
Search Analytics
search_analytics
Get search performance data.
siteUrl(required): Site URL (e.g.,https://example.comorsc-domain:example.com)startDate(required): Start date (YYYY-MM-DD)endDate(required): End date (YYYY-MM-DD)account(optional): Account to usedimensions(optional): query, page, country, device, daterowLimit(optional): Max 25,000 rowspageFilter,queryFilter,countryFilter,deviceFilterfilterOperator: equals, contains, includingRegex, excludingRegex
detect_quick_wins
Find SEO optimization opportunities - keywords ranking 4-20 with high impressions but low CTR.
siteUrl,startDate,endDate(required)minImpressions(default: 100)maxCtr(default: 3.0%)positionRangeMin/Max(default: 4-20)limit(default: 50)
compare_periods
Compare metrics between two time periods.
siteUrl(required)currentStartDate,currentEndDate(required)previousStartDate,previousEndDate(required)dimensions(optional)
URL Management
inspect_url
Check URL indexing status.
siteUrl,inspectionUrl(required)
submit_url_for_indexing
Submit URL for Google indexing (requires Indexing API enabled).
url(required)type: URL_UPDATED (index) or URL_DELETED (remove)
Sitemaps
list_sitemaps
List sitemaps for a site.
siteUrl(required)
submit_sitemap
Submit a sitemap.
siteUrl,feedpath(required)
Getting OAuth Credentials
- Go to Google Cloud Console
- Create or select a project
- Enable Search Console API and Indexing API
- Go to Credentials β Create Credentials β OAuth 2.0 Client ID
- Application type: Desktop app
- Download the credentials
Getting a Refresh Token
Use the Google OAuth Playground or run:
npx -y google-search-console-mcp-server google-search-console-mcp-setup
Examples
"List my GSC accounts"
"Show quick wins for https://example.com using the main account"
"Compare last 7 days vs previous 7 days for sc-domain:example.com"
"Submit https://example.com/new-article for indexing"
"Get top 100 queries for https://example.com from 2024-01-01 to 2024-01-31"
License
MIT
Contributing
Contributions welcome! Please read the contributing guidelines first.
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.