mcp-gsc

<!-- Logo (referenced by the Cline/Glama submissions): add assets/logo.png (400x400), then uncomment: <img src="assets/logo.png" alt="mcp-gsc logo" width="120" align="right"> -->

Connect in 30 seconds

Every deployed instance exposes the same endpoint shape:

https://<your-worker>.workers.dev/mcp

Claude Code

claude mcp add --transport http gsc https://<your-worker>.workers.dev/mcp

Cursor

<!-- The config param is base64 of {"url":"https://REPLACE-ME.workers.dev/mcp"}. When the canonical hosted URL replaces the placeholder, regenerate it with: node -e "console.log(Buffer.from(JSON.stringify({url:'https://<real-host>/mcp'})).toString('base64'))" -->

ChatGPT — add it as a custom connector; see Connect in your AI client below.

A self-hostable Model Context Protocol (MCP) server for Google Search Console. Connect it to Claude.ai, Cursor, ChatGPT, or any MCP-compatible client and ask your AI assistant about your site's organic search performance — impressions, clicks, top queries, index status, and sitemap health — straight from your own Google account.

It runs on Cloudflare Workers and ships with one-click Google OAuth onboarding: connect the server in your client, sign in with Google once, grant the requested Google Search Console permissions, and you're done. No API keys to copy around and no service-account JSON to manage.

Prefer zero setup? The hosted version — with automatic weekly email digests delivered to your inbox — is at digestseo.com. This repository is the open-source core you can run yourself.

Tools

This server exposes 17 tools. Read-only analytics and reporting tools are marked with MCP's readOnlyHint; the write tools below can change Search Console properties, sitemaps, or indexing state.

Tool	Access	What it does
get_capabilities	Read	List every tool this server exposes and report whether your Google connection is currently authenticated (connected / not_connected). Takes no arguments — a good first call for discovery.
list_sites	Read	List the Search Console properties the connected Google account can access (siteUrl, permissionLevel).
query_search_analytics	Read	Impressions, clicks, CTR, and average position over a date range, with dimensions, filters, pagination, and selectable search type.
inspect_url	Read	Google's URL Inspection report for a single page.
list_sitemaps / get_sitemap	Read	List submitted sitemaps or retrieve one sitemap's details.
identify_quick_wins / detect_cannibalization / detect_content_decay	Read	Surface optimization opportunities, competing pages, and declining content.
list_indexed_pages / compare_performance	Read	Analyze pages receiving impressions and compare two periods.
weekly_digest	Read	Generate a plain-language seven-day performance report with movers, top pages, and one recommended action.
add_site / delete_site	Write	Add or remove a Search Console property.
submit_sitemap / delete_sitemap	Write	Submit or remove a sitemap.
request_indexing	Write	Request indexing for an eligible URL through the Google Indexing API.

The server requests Google Search Console and Indexing API scopes. Use a Google account with only the property access you intend to delegate, and review write-tool calls before approving them.

What you can ask

Once connected, ask your assistant things like:

• "What are my top 20 queries by clicks in the last 28 days?"
• "Compare impressions for example.com this month vs last month — which pages dropped?"
• "Is https://example.com/pricing indexed? When was it last crawled?"
• "Which queries does my blog rank position 5–15 for? Those are my quick wins."
• "Give me a weekly digest for sc-domain:example.com ending today."
• "Do any of my sitemaps have errors or warnings?"
• "Split my clicks into brand vs non-brand using a regex on the query."
• "How is my site doing in Google Discover vs regular web search?"

Connect in your AI client

Once you've deployed the server (see SETUP.md), connect it by pasting your Worker's /mcp URL into your client:

https://<your-worker>.workers.dev/mcp

• Claude.ai — Settings → Connectors → Add custom connector → paste the /mcp URL. Leave Client ID and Client Secret blank. On first use, Claude opens a Google sign-in flow; grant read access and the connector turns green.
• Cursor — add it as a custom MCP server pointing at the same /mcp URL.
• ChatGPT (with connector/MCP support) — add a custom connector with the /mcp URL.

Any MCP-compatible client works — they all point at the same /mcp endpoint and share the same OAuth flow.

Setup

Self-hosting means bringing your own Google OAuth credentials and Cloudflare account. The full, copy-pasteable walkthrough is in SETUP.md — including an important note about Google's OAuth verification and the 7-day refresh-token limit while your app is unverified.

Quick shape:

git clone https://github.com/<you>/mcp-gsc.git
cd mcp-gsc
npm install
cp wrangler.example.jsonc wrangler.jsonc       # then paste in your KV ids
# set GOOGLE_CLIENT_ID / GOOGLE_CLIENT_SECRET / TOKEN_ENCRYPTION_KEY as secrets
npm run deploy

See SETUP.md for every step in detail.

Development

npm install
npm test              # typecheck + offline unit tests (what CI runs)
npm run dev           # wrangler dev (local)
npm run test:smoke    # structural smoke tests against a deployment

Contributions welcome — see CONTRIBUTING.md.

License

MIT © 2026 DigestSEO.

---

Built and maintained by Tomi Šeregi, the builder behind digestseo.com — weekly SEO digests for non-technical site owners.