Google Search Console MCP Server

<!-- mcp-name: io.github.onlymoein/google-search-console-mcp -->

A local Model Context Protocol server that connects AI assistants (Claude Code, Claude Desktop, Cursor and any other MCP client) to the Google Search Console API. Ask about clicks, queries, pages, indexing and sitemaps in plain language; the server turns that into correct API calls and returns structured data.

It runs on your machine and talks to Google; the only other site it reads is your own, during an indexing audit. It stores your login and your audits' progress, nothing else.

Unofficial. This project is not affiliated with or endorsed by Google. You use your own Google Cloud credentials and are responsible for your usage under Google's terms.

Why this one

• It catches the API's traps. Google answers many bad requests with an empty result instead of an error: an invalid regex, a two-letter country code, hourly data older than ten days, a range in the future. Other combinations fail with a terse 400. Every one of these is checked before the call and explained in plain words. The rules are verified against the live API, not copied from blog posts.
• It explains changes, not just numbers. explain_change splits a rise or fall by page, query, country, device and search appearance, separates lost impressions from a lower click-through rate, and lines the change up with Google's published updates.
• Full indexing audits. Google's API does not expose the Page indexing report's URL lists, so audit_indexing rebuilds them: it inspects every sitemap URL within the daily quota, carries on where it stopped the next day, and can check each live page against what Google last saw.
• Everything the API can do, with guard rails. Reads and writes are both on: it can add and remove properties and submit and remove sitemaps. Changes need the property's exact name, and the tools that make them are marked as writes (deletes as destructive), which clients can use to ask before running them. Turn writes off with GSC_ENABLE_WRITES=0.
• Structured output. Every tool declares an output schema, rows come back as named fields, and every analytics result includes the exact request sent to Google.
• Full API coverage: search analytics (all search types, filters, data states, pagination), hourly data, search appearances, URL inspection (single and concurrent batch), sitemaps and properties, plus a dedicated tool for each search surface (Discover, Images, video, Google News, the News tab) that only accepts what that surface supports.
• Built on the current stack: MCP Python SDK 2.x (protocol 2026-07-28 and older clients alike) and an async client, so batch inspection runs concurrently.

Quick start

You need uv and a Google account with access to at least one Search Console property.

1. Create an OAuth client in Google Cloud (about five minutes, once):

   1. Open console.cloud.google.com and create or pick a project.
   2. APIs & Services > Library: enable the Google Search Console API.
   3. Google Auth Platform > Branding: fill in an app name and your email.
   4. Google Auth Platform > Audience: choose External, add your Google account as a test user, then click Publish app so the status is In production. Skip this and Google expires your login every 7 days.
   5. Google Auth Platform > Clients > Create client: type Desktop app. Download the JSON and keep it outside any repository, for example ~/.config/open-gsc-mcp/client_secret.json.

2. Sign in (opens a browser once; the server itself never does):

   uvx open-gsc-mcp@latest auth login --client-file ~/.config/open-gsc-mcp/client_secret.json
   

   Google shows "Google hasn't verified this app" because the app is yours and unreviewed; choose Advanced > Go to (your app). When it finishes, the command lists the properties it can see.

3. Add the server to your client (below), restart the client, and ask something like "Which queries lost the most clicks this month on example.com?"

Client configuration

Claude Code

claude mcp add --scope user gsc -- uvx open-gsc-mcp@latest

Claude Desktop: edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

{
  "mcpServers": {
    "gsc": {
      "command": "uvx",
      "args": ["open-gsc-mcp@latest"]
    }
  }
}

If Claude Desktop reports that uvx cannot be found, use its absolute path (which uvx on macOS and Linux, where uvx on Windows).

Cursor: add the same mcpServers block to ~/.cursor/mcp.json.

@latest makes uvx check for a new release each time the client starts the server. Without it, uvx keeps running the version it cached the first time. To upgrade only when you choose, pin a version instead, such as open-gsc-mcp@1.2.0.

To pass settings, add an env object to the server entry, or -e NAME=value to claude mcp add. Paths must be absolute: clients start the server from an arbitrary working directory.

Service account (headless)

For servers, CI or shared machines, use a service account instead of a personal login:

1. In Google Cloud, IAM & Admin > Service Accounts: create one, then Keys > Add key > JSON. (Some organizations block key creation by policy.)

2. In Search Console, Settings > Users and permissions > Add user: add the service account's email to each property, with Full or Restricted permission.

3. Point the server at the key:

   claude mcp add --scope user gsc -e GSC_SERVICE_ACCOUNT_FILE=/abs/path/key.json -- uvx open-gsc-mcp@latest
   

When GSC_SERVICE_ACCOUNT_FILE is set it takes precedence over any OAuth login.

Tools

| Tool | What it does | |---|---| | list_sites | Properties this account can access, with exact site_url and permission level. | | get_site | One property's type and permission level. | | query_search_analytics | Clicks, impressions, CTR and position by query, page, country, device, date or search appearance; any search type; filters; final or all data; paging. | | query_hourly_analytics | The same, by hour, for the last ~10 days. Reports where incomplete hours start. | | query_discover_analytics | Google Discover by page, country or date. No query, device or position, so the tool doesn't offer them. | | query_image_analytics | Google Images: queries, pages and positions within image results. | | query_video_analytics | The Videos tab of Google Search. | | query_google_news_analytics | Google News (news.google.com and the app) by page, country, device or date. No query or position. | | query_news_tab_analytics | The News tab of Google Search, with queries and positions. | | list_search_appearances | Rich results and other result features the property had: step one of Google's two-step appearance query. | | query_search_appearance | Step two: one appearance broken down by query, page, country, device or date. | | compare_periods | Two equal-length periods: totals and per-key changes, absolute and percent, biggest movers first. | | explain_change | Why traffic moved between two periods: which pages, queries, countries, devices and search appearances account for it, how much came from impressions versus click-through rate, and Google updates in or near the periods. | | inspect_url | Index status, coverage, canonical (Google's versus yours), crawl, robots.txt and rich results for one URL. | | batch_inspect_urls | Up to 50 URLs concurrently, with progress, per-URL errors and a verdict summary. Stops cleanly when the quota runs out. | | audit_indexing | Every sitemap URL, inspected over as many calls and days as it takes and grouped by index status with likely fixes; canonical conflicts, indexed pages with no impressions, pages missing from the sitemaps; optionally a live check of each page. | | list_sitemaps, get_sitemap | Submitted sitemaps with errors, warnings, pending state and URL counts. |

query_news_analytics from 1.1.0 is deprecated: calls still work and go to the new news tool its source selects, until it is removed in 2.0.0.

Four tools make changes: submit_sitemap, delete_sitemap, add_site and delete_site. They accept only a property's exact site_url, and a sitemap must belong to that property. They are annotated as writes (deletes as destructive) and tell the model to confirm with you first, but the server does not ask you itself: whether you see a prompt depends on your client's permission settings. These four are every change Google's API allows: it cannot request indexing, remove URLs from search, or manage users and settings. Set GSC_ENABLE_WRITES=0 for a server without them.

Sites can be given as sc-domain:example.com, https://www.example.com/, a bare example.com, or any URL on the site. Anything but the exact property is resolved against your real property list, to the property that contains it; results then say so, and for a page URL they note that they cover the whole property.

Prompts: weekly_report, indexing_audit and content_opportunities are ready-made workflows with concrete dates and exact tool calls.

Indexing audits save their progress locally, so each audit_indexing call carries on where the last one stopped. Inspections take a few seconds each, so a call covers about 50 URLs; for a large site, run uvx open-gsc-mcp@latest audit sc-domain:example.com in a terminal (or daily from cron) to use the full 2,000 a day, then ask your assistant about the results.

Configuration

| Variable | Default | Purpose | |---|---|---| | GSC_SERVICE_ACCOUNT_FILE | unset | Service account key; when set, it is used instead of OAuth. | | GSC_OAUTH_CLIENT_FILE | unset | OAuth client JSON, so auth login needs no --client-file. | | GSC_TOKEN_FILE | per-user config dir | Where auth login saves the login (mode 0600). | | GSC_ENABLE_WRITES | 1 | Set to 0 to leave out the four tools that make changes; auth login then asks only for read access. | | GSC_LOG_LEVEL | INFO | DEBUG also logs every HTTP request. Logs go to stderr. | | GSC_DATA_DIR | per-user data dir | Where indexing audits keep their progress (one SQLite file, owner-only). |

Command line:

uvx open-gsc-mcp@latest              # run the MCP server over stdio (what clients do)
uvx open-gsc-mcp@latest auth login   # sign in; --read-only to grant reads only, --no-browser over SSH
uvx open-gsc-mcp@latest auth status  # which credentials are used, and do they work
uvx open-gsc-mcp@latest auth logout  # revoke and delete the saved login
uvx open-gsc-mcp@latest audit SITE   # inspect up to a day's 2,000 sitemap URLs; --fetch-pages

API behavior handled for you

| Google's behavior | What the server does | |---|---| | searchAppearance cannot be grouped with any other dimension (400). | Rejects it and points to the two-step pattern. | | notEquals/notContains on searchAppearance return the rows you meant to exclude (a confirmed Google bug). | Rejects them with an explanation. | | Discover and Google News have no query data (400) and no position; Discover has no device data (40