gsc-mcp
Turns Google Search Console into an SEO copilot by enabling natural language queries for search analytics, URL inspection, sitemap management, and opportunity discovery.
README
gsc-mcp
A Model Context Protocol (MCP) server that turns Google Search Console into an SEO copilot for any MCP client (Claude Desktop, Claude Code, Cursor, …). Query search analytics, inspect URLs, manage sitemaps, switch between properties, and surface SEO opportunities — in plain language.
Status: Phase 1. The GSC data layer + multi-site + onboarding are built and working. Coverage-report reconstruction, on-page audits, page-speed, scoring, and a dashboard are on the roadmap — see SPEC.md.
Install & connect (Tier 0: bring-your-own Google client)
A hosted "just sign in" client is coming; for now you create a one-time Google Cloud client.
1. Google Cloud (once):
- Create or pick a project at https://console.cloud.google.com/.
- Enable the Google Search Console API (and, later, the PageSpeed Insights API).
- OAuth consent screen → External → add your Google account as a test user (test users skip app verification).
- Credentials → Create OAuth client ID → type Desktop app.
- Copy the Client ID and Client secret.
2. Sign in (once):
GSC_OAUTH_CLIENT_ID=xxx GSC_OAUTH_CLIENT_SECRET=yyy npx -y @ajmalaksar/gsc-mcp login
A browser opens; approve access. The token is stored at ~/.gsc-mcp/token.json (mode 0600). You can also let Claude do this in-conversation with the auth_login tool.
3. Add to your MCP client (Claude Desktop / generic):
{
"mcpServers": {
"gsc": {
"command": "npx",
"args": ["-y", "@ajmalaksar/gsc-mcp", "serve"],
"env": {
"GSC_OAUTH_CLIENT_ID": "xxx",
"GSC_OAUTH_CLIENT_SECRET": "yyy",
"GSC_DEFAULT_SITE": "sc-domain:example.com"
}
}
}
}
Claude Code one-liner: claude mcp add gsc -- npx -y @ajmalaksar/gsc-mcp serve.
CLI
gsc-mcp login Sign in with Google (opens a browser)
gsc-mcp logout Remove the stored token
gsc-mcp status Authentication + onboarding status
gsc-mcp setup Guided first-run
gsc-mcp sites … Manage the property registry (list / add / remove / default)
gsc-mcp serve Start the MCP server over stdio (default)
Multi-site
siteUrl is optional on every tool. It resolves in order: explicit arg → session active site → persisted default. Register friendly aliases so you can say "the blog":
gsc-mcp sites add blog sc-domain:example.com
gsc-mcp sites default blog
In chat: use_site switches the active property; account_overview gives a portfolio view across all properties.
Tools
auth_status, auth_login, list_sites, use_site, get_active_site, set_default_site, account_overview, gsc_deep_link, query_search_analytics, top_queries, top_pages, find_opportunities, compare_periods, inspect_url, coverage_report, refresh_coverage, get_pages_in_bucket, list_sitemaps, get_sitemap. With GSC_ENABLE_WRITE=1: submit_sitemap, delete_sitemap.
Coverage report (refresh_coverage → coverage_report → get_pages_in_bucket) reconstructs the "Page indexing" report the GSC API won't export in bulk: it gathers candidate URLs from your sitemaps and analytics, inspects them within the 2,000/day per-property quota (resumable), caches the results under ~/.gsc-mcp/sites/, and buckets them by index status.
Develop & extend
npm install
npm run build
npm test
The server is a tool registry. To add a capability, create src/tools/<group>.ts exporting register: ToolModule, then add it to MODULES in src/tools/index.ts. Each module receives the McpServer and a shared ToolContext (auth, GSC client, site resolution). See the architecture notes in SPEC.md.
License
MIT © Ajmal Aksar
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.