GSC MCP
MCP server for Google Site Verification and Search Console. Enables site verification, property management, and sitemap submission through MCP tools.
README
GSC MCP
An extensible Model Context Protocol (MCP) server for Google Site Verification and Google Search Console. It uses the MCP Streamable HTTP transport and keeps Google OAuth credentials and tokens local.
Available tools
| Tool | Purpose |
|---|---|
get_verification_token |
Get a FILE or META verification token for a URL-prefix site |
verify_site |
Verify site ownership after the file or meta tag is live |
add_site_to_search_console |
Add a verified URL-prefix property |
submit_sitemap |
Submit a sitemap for a property |
list_sites |
List Search Console properties |
list_sitemaps |
List submitted sitemaps and their status |
Requirements
- Node.js 20 or newer
- A Google Cloud OAuth Desktop client
- Site Verification API and Search Console API enabled in the Google Cloud project
Setup
npm ci
cp .env.example .env
Fill GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET in .env, then generate a strong MCP bearer token:
node -e "console.log(require('crypto').randomBytes(32).toString('hex'))"
Put the generated value in MCP_AUTH_TOKEN, authorize Google once, and start the server:
npm run auth
npm start
The endpoints are:
- MCP:
http://127.0.0.1:8787/mcp - Health:
http://127.0.0.1:8787/health
MCP requests must include Authorization: Bearer <MCP_AUTH_TOKEN>. To connect a remote MCP client, expose the local endpoint through a trusted HTTPS tunnel and keep bearer authentication enabled.
Architecture
src/index.js runtime composition
src/http-server.js HTTP transport and bearer auth
src/server.js MCP server construction
src/google-client.js reusable Google OAuth/API client
src/tools/index.js central tool registry
src/tools/google-search-console.js
Search Console tool module
To add another MCP capability:
- Create one registrar module in
src/tools/. - Export a function with the signature
registerFeatureTools(server, dependencies). - Add that registrar to
src/tools/index.js. - Add contract tests under
test/.
Keep API clients outside tool modules and inject them as dependencies. This keeps tools testable and prevents credentials from becoming part of the MCP layer.
Validation
npm test
npm run security:check
npm run check
CI runs the same deterministic checks on every push and pull request.
Security
.env, token*.json, client_secret*.json, private keys, dependencies, and logs are excluded from Git. The secret check scans only tracked files and fails on blocked credential filenames or high-confidence token patterns. See SECURITY.md.
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.