gsc-mcp

gsc-mcp

Enables programmatic management of Google Search Console properties and IndexNow URL submission for search indexing.

Category
Visit Server

README

gsc-mcp

MCP server for Google Search Console and IndexNow — manage search indexing programmatically instead of driving a browser.

  • Image: ghcr.io/robertdwhite/gsc-mcp, built by CI in this repo.
  • Transport: MCP streamable HTTP at /mcp, bearer-gated by MCP_TOKEN. /healthz is open.

Tools

Tool Does
gsc_status() Credential check; reports the service-account email
list_sites() / add_site(site_url) Search Console properties
verification_token(site_url, method) Get FILE/META ownership token
verify_site(site_url, method) Complete verification — the service account becomes an owner
add_owner(site_url, email) Grant a human Google account access (UI + API)
submit_sitemap(site_url, sitemap_url) / list_sitemaps(site_url) Sitemap management with indexed-count stats
search_analytics(site_url, days, dimensions, row_limit) Clicks/impressions/CTR/position by query, page, country, device, date
inspect_url(site_url, url) Per-URL index status, last crawl, canonical
submit_indexnow(urls, host, key) Push URLs to Bing/DuckDuckGo/Yandex — works with no Google setup

One-time Google setup (human, ~5 minutes)

  1. In Google Cloud Console, create/reuse a project and enable Google Search Console API and Site Verification API.
  2. Create a service account (no roles needed) and a JSON key.
  3. Put the key JSON in the GSC_SA_JSON env var (in-cluster: the gsc-mcp-env secret).

Then, via tools: add_site → verification_token (place the token on the site) → verify_site → the service account is a verified owner and every other tool works. add_owner grants your personal account the same property.

Config (env)

Var Meaning
MCP_TOKEN Bearer token required on /mcp. Unset = unauthenticated (dev only).
GSC_SA_JSON Service-account key JSON (the raw JSON string).
INDEXNOW_HOST / INDEXNOW_KEY Optional defaults for submit_indexnow.
PORT Listen port (default 8080).

Deploy

Manifests live in whitehouse-rke2 under apps/ai/gsc-mcp (endpoint https://gsc-mcp.internal.white.fm/mcp, tailnet only).

Connecting clients

The server speaks MCP streamable HTTP at /mcp and expects Authorization: Bearer <MCP_TOKEN>. Anything below works from any machine that can reach the endpoint (for the house deploy: tailnet/LAN only).

Claude Code

claude mcp add --transport http gsc https://gsc-mcp.internal.white.fm/mcp \
  --header "Authorization: Bearer <MCP_TOKEN>"

Or directly in ~/.claude.json:

"mcpServers": {
  "gsc": {
    "type": "http",
    "url": "https://gsc-mcp.internal.white.fm/mcp",
    "headers": { "Authorization": "Bearer <MCP_TOKEN>" }
  }
}

Claude Desktop

The custom-connector UI expects OAuth; this server uses a static bearer, so bridge it with mcp-remote in claude_desktop_config.json (needs Node):

"mcpServers": {
  "gsc": {
    "command": "npx",
    "args": ["-y", "mcp-remote", "https://gsc-mcp.internal.white.fm/mcp",
             "--transport", "http-only",
             "--header", "Authorization: Bearer <MCP_TOKEN>"]
  }
}

Codex (ChatGPT app / Codex CLI)

Codex configures MCP servers as stdio commands — use the same bridge in ~/.codex/config.toml:

[mcp_servers.gsc]
command = "npx"
args = ["-y", "mcp-remote", "https://gsc-mcp.internal.white.fm/mcp",
        "--transport", "http-only",
        "--header", "Authorization: Bearer <MCP_TOKEN>"]
startup_timeout_sec = 60

Restart the app after editing.

Hermes (or any YAML-config MCP client)

mcp_servers:
  gsc:
    url: https://gsc-mcp.internal.white.fm/mcp
    headers:
      Authorization: Bearer ${GSC_MCP_TOKEN}

Sanity check without a client

curl -s https://gsc-mcp.internal.white.fm/healthz   # -> ok (no auth)
curl -s -o /dev/null -w '%{http_code}\n' -X POST \
  https://gsc-mcp.internal.white.fm/mcp             # -> 401 (auth gate works)

Note: claude.ai web connectors cannot reach a tailnet-only endpoint; expose an external route first if you need it there.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured