Google Search Console MCP Server & CLI

What is the Google Search Console MCP server & CLI?

The Google Search Console MCP server & CLI is a free, open source program that lets AI agents read your search traffic and manage your Search Console properties for you, in 2 ways. The MCP server is what an AI app like Claude, Codex or Cursor connects to, through MCP (Model Context Protocol), the open standard AI apps use to call outside tools.

You ask in plain language. Your AI picks the right tool, and the server makes the call to Google's Search Console API.

The CLI is the same program as commands. google-search-console-cli top-queries --site sc-domain:example.com runs the same code your AI runs when you ask for your top queries, whether an agent like Claude Code runs it or you do.

What can you ask it?

Once it's set up, you ask the way you'd ask an assistant. These are real prompts it handles:

Try asking
Which queries lost the most clicks this month compared to last?
Show me pages ranking between 5 and 20. Which are closest to page one?
Why is this URL not showing up in Google?
Is Google still reading my sitemap?
We just launched 30 pages. Check which ones are indexed.
Which of my pages get impressions but almost no clicks?

The first one shows why this is useful. Search Console's own screens make you export two reports and join them in a spreadsheet to answer it, and here it's one call with the changes already worked out.

How to install the Google Search Console MCP server

Pick your app in the box at the top of this page. Each one is a single command or a pasted block, after you sign in once with your own Google OAuth client.

Set up Google Search Console

Google only gives Search Console access through a Google Cloud project, so there is a real setup here. It takes about 5 minutes, once.

The refresh token is saved to ~/.google-search-console-mcp/tokens.json, and every app on this computer uses it from then on. For a server with no browser, a service account key in GSC_SERVICE_ACCOUNT_KEY works instead. The full walkthrough is in the repo's INSTALL.md.

Check that it works

Run the doctor. It checks which credential is in use, whether a token can be minted, and how many properties that account reaches.

npx -y @thenavidm/google-search-console-mcp-cli doctor

Zero properties means you signed in with the wrong Google account. A refresh failure a week after setup means the OAuth app is still in Testing.

Use the Google Search Console CLI

The CLI is the same 19 tools as commands. AI agents that run commands, like Claude Code, Codex and OpenCode, use it on their own, and you can type the same commands in a terminal or a script.

Every tool name becomes a command with dashes, so striking_distance runs as google-search-console-cli striking-distance.

npm install -g @thenavidm/google-search-console-mcp-cli
google-search-console-cli
google-search-console-cli list-sites
google-search-console-cli top-queries --site sc-domain:example.com --limit 10
google-search-console-cli compare-periods --site sc-domain:example.com

The bare google-search-console-cli lists every command, and google-search-console-cli <command> --help shows what a command takes. Deleting a property or a sitemap asks for --confirm first, like it does for your AI.

These flags work on every command:

A script can branch on the exit code:

MCP server or CLI: which one?

Both are the same program with the same 19 tools. The difference is when your AI pays for them, in the tokens it reads.

An app that loads every tool up front sends the full list with every message, whether you mention Google Search Console or not. Claude Code doesn't by default: its tool search sends only the tool names and the server's instructions, and loads a tool's full definition when your AI reaches for it.

The CLI costs nothing until Google Search Console comes up. Then your agent reads its skill file once and runs the commands it needs. With the skill added, Claude Code also lists its one-line description with every message, about 190 tokens.

When the whole conversation is about Google Search Console, the gap closes. Then the MCP server is the better experience, because you ask in plain language and your AI never has to look up a command.

How to spend less

In Claude Code, leave tool search on, which it is unless you've set ENABLE_TOOL_SEARCH=false.

Turn the server off when you aren't using it, with your AI app's own switch. GSC_READ_ONLY=1 also takes the 5 write tools off the list.

Or install the CLI and connect the server later, on the days it earns its place. Every tool stays in reach, and the standing cost drops to nothing.

Every number here was measured on September 27, 2026 in Claude Code 2.1.257 with Claude Opus 5. It's the same one-line prompt with and without the server connected, once with tool search off so every tool loads, and once with Claude Code's default. The skill was measured the same way, and other apps and models count tokens a little differently.

What Search Console actually does

A few things cost people an afternoon, and the tools are built around them.

The data runs 2 to 3 days behind

A window that ends today looks empty or partial for its last few days. Every tool with a default window ends 3 days back and says which dates it used.

Queries never add up to the site total

Google holds back rare queries to protect the people who typed them, so a per-query report always shows fewer clicks than the property total. That gap is hidden traffic, not missing traffic.

A property isn't a website

https://example.com/ and sc-domain:example.com are different properties with different data. Passing the wrong one returns "User does not have sufficient permission", so copy the exact string from list_sites.

Lower position is better

Average position is a rank, so moving from 8 to 5 is an improvement. compare_periods signs its position change so that positive always means better.

There's no "request indexing" button in the API

Google offers none. Resubmitting a sitemap is the only recrawl signal an API can send, which is what submit_sitemap is for.

Quotas are per property

Search analytics allows roughly 1,200 queries a minute. URL inspection allows about 2,000 a day and 600 a minute, so inspect_urls paces itself.

Every Google Search Console tool

All 19 tools, grouped the way the repo groups them. 14 only read, and 5 change something in Search Console.

Search analytics

URL inspection

Sitemaps

Properties and accounts

Verification

Is the Google Search Console MCP server safe?

Writes work from the start, because submitting a sitemap is the point of the tool. Adding a property and submitting a sitemap are easy to undo, so they don't ask.

delete_site and delete_sitemap can't be undone, so both ask for a confirm check first, marked Asks first in the tool tables above.

Make it read-only

Set GSC_READ_ONLY=1 and every write disappears from the tool list, leaving 14 reading tools. GSC_ALLOW_DESTRUCTIVE=0 keeps the sitemap and property writes and drops the 2 deletes.

Keep a log of every write

Set GSC_AUDIT_LOG to a file path. The server writes one line per attempted write, allowed or blocked.

Your data

There's no server of ours in between. Requests go straight from your computer to Google, and Search Console data is read on demand and never saved to disk.

The refresh token lives in ~/.google-search-console-mcp/tokens.json, readable only by you. logout deletes it, and myaccount.google.com/permissions revokes Google's side, which is the half that matters.

Google Search Console MCP server settings

Every setting is an environment variable in your app's config or your shell. After login, none of them are required.

Troubleshooting

Run the doctor first. It names the step that failed and the fix.

If the server doesn't show up in your app at all, run the command your app runs, in a terminal, and read the error.