Google Search Console vs Google Search Console MCP
A side-by-side look at the Google Search Console and Google Search Console MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Google Search Console for marketing work as a local process; choose Google Search Console MCP for marketing as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Google Search Console when
- You need dedicated capabilities in the Marketing domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, TOKEN_ENCRYPTION_KEY. - You want tools like
server.capabilities, sites.list, sites.get.
Choose Google Search Console MCP when
- You need dedicated capabilities in the Marketing domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: OAuth 2.0.
- You have the keys it needs:
GSC_CLIENT_ID, GSC_CLIENT_SECRET, GSC_REFRESH_TOKEN. - You want tools like
gsc_sites, gsc_site_details, gsc_query.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Marketing | Marketing |
| Quality signal | 59/100 · Good | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | OAuth 2.0 |
| Pricing | Not declared | Free |
| Required env vars | GOOGLE_CLIENT_IDGOOGLE_CLIENT_SECRETTOKEN_ENCRYPTION_KEY | GSC_CLIENT_IDGSC_CLIENT_SECRETGSC_REFRESH_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | 5 | 9 |
| Directory activity | 1 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 10 | 17 |
| Full listing | View Google Search Console | View Google Search Console MCP |
Tools & capabilities
Google Search Console tools 10
server.capabilitiesList every tool this server exposes and report local Google credential state. `connected` means a stored refresh credential is present; the response also exposes `auth_status_basis` and `provider_auth_live_verified: false` because this discovery call does not probe Google. A later Google tool call…sites.listList the Search Console properties the connected Google account can access (`siteUrl`, `permissionLevel`).sites.getRetrieve one exact Search Console property and the connected account's permission level for it.analytics.queryImpressions, clicks, CTR, and average position over a date range, with dimensions, filters, safe pagination, and selectable search type. Pass `dimensions: []` for true site totals; Google's aggregate row may omit `keys`. Search Analytics does not guarantee every data row and can return only top row…urls.inspectGoogle's URL Inspection report for the version of one page currently known in Google's index. It is not a live URL test; mobile-usability output is deprecated.urls.inspect_manyInspect Google's indexed versions of up to 10 URLs with bounded concurrency of 3 in one call while preserving input-order results. Each URL still consumes one Google URL Inspection request and one unit of the server's shared inspection safety budget; this does not run live URL tests.reports.weekly_digestGenerate a plain-language seven-day performance report with movers, top pages, and one recommended action. Query movers compare only rows returned in both weekly Search Analytics result sets; a query missing from one bounded response is not treated as zero because Google does not guarantee every da…indexing.statusRead Google's latest successful Indexing API `URL_UPDATED` / `URL_DELETED` notification receipts for a previously submitted URL. This is notification metadata only, not index coverage, crawl status, indexing completion, or removal completion. It requires `GSC_ACCESS_MODE=readwrite` because Google's…indexing.requestRequests indexing through Google's Indexing API. Google currently restricts this API to pages containing `JobPosting` structured data or livestream pages containing `BroadcastEvent` inside `VideoObject`. It is not available for general webpage submission. Google's default 200 publish requests/day/p…indexing.removeRequest a `URL_DELETED` notification for a previously eligible Indexing API page. Before removal, the URL must already return HTTP 404/410 or expose a robots `noindex` meta directive. Google's receipt does not prove removal completed; use URL Inspection for indexed-state evidence.
Google Search Console MCP tools 17
gsc_sitesList every property the authenticated account can read. Call this first when a property string fails: it returns the exact `site_url` values the other tools expect, and whether each one is a domain property (`sc-domain:example.com`) or a URL-prefix property.gsc_site_detailsPermission level and property type for one property.gsc_queryQuery the Search Analytics report: clicks, impressions, CTR, position. This is the general-purpose tool. With no dates it covers the last 28 days ending today (UTC), with data_state=all so today's partial data is included, matching what the Search Console UI shows. Example: site_url="sc-domain:example.com", dimensions="query,page", period="last_28_days", row_limit=100. Returns a `# meta ...` line then a TSV table, or JSON with `meta` and `rows`. The meta names the exact range, the row count, whether more rows exist and the `start_row` to pass next.gsc_performance_overviewSite totals for a period, compared with the preceding one by default. Start here: it answers "is the site up or down" in one call, with the percentage change on every metric. `position_delta` is negative when the average position improves.gsc_compare_periodsJoin two periods on one dimension and rank the rows by click delta. Answers "what changed" without the model diffing two tables by hand. Rows present in only one period are kept, with zeros on the missing side; the biggest movers in both directions are returned, worst first. The meta counts how many rows gained and how many lost clicks.gsc_quick_winsQueries close enough to the top that a push would pay off. Ranked by the clicks each query would gain at `target_position`, not by impressions: a big query already near its ceiling is not an opportunity. The meta reports the thresholds that were applied.gsc_ctr_gapsRows that rank well but are clicked far less than their position implies. The snippet, not the ranking, is the problem, which makes these the cheapest fixes available. `expected_ctr` is what a result at that position normally earns.gsc_cannibalizationQueries where several pages of the site compete for the same result. Reads one page of up to 25,000 query/page pairs; on a very large property the tail is cut off, and the meta says how many pairs were analysed. Each row lists the competing pages with their own clicks and positions.gsc_traffic_dropsPages that lost clicks against the baseline, each with a likely cause. `diagnosis` separates a ranking loss from falling demand, a collapsed CTR and a page that disappeared: the four need different fixes, and the raw numbers for both periods are in the row so the call can be checked.gsc_content_decayPages sliding down month after month. A period comparison hides this: a page that halves over six months never shows a sharp drop in any single month-on-month check. One query per month runs in parallel.gsc_alertsWhat changed sharply enough to be worth a message today. Compares the last `window_days` against the window before it across both queries and pages, and returns only movements past the alerting rules: lost positions, collapsed CTR, dropped or vanished pages.gsc_portfolioEvery accessible property at a glance, ranked worst first. One row per property with the current period, the previous one and a health flag: critical below -30% clicks, warning below -15%. Use it to decide which property to look at before running anything else.- +5 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Google Search Console
{
"mcpServers": {
"google-search-console": {
"command": "npx",
"args": [
"-y",
"@digestseo/mcp-gsc"
],
"env": {
"GOOGLE_CLIENT_ID": "YOUR_GOOGLE_CLIENT_ID_HERE",
"GOOGLE_CLIENT_SECRET": "YOUR_GOOGLE_CLIENT_SECRET_HERE",
"TOKEN_ENCRYPTION_KEY": "YOUR_TOKEN_ENCRYPTION_KEY_HERE"
}
}
}
}
Google Search Console MCP
{
"mcpServers": {
"acamolese-google-search-console-mcp": {
"command": "uvx",
"args": [
"mcp-google-search-console"
],
"env": {
"GSC_CLIENT_ID": "YOUR_GSC_CLIENT_ID_HERE",
"GSC_CLIENT_SECRET": "YOUR_GSC_CLIENT_SECRET_HERE",
"GSC_REFRESH_TOKEN": "YOUR_GSC_REFRESH_TOKEN_HERE"
}
}
}
}
Frequently asked questions
Google Search Console is categorized under Marketing and uses a local stdio subprocess. Google Search Console MCP belongs to Marketing and uses a local stdio subprocess. Pick Google Search Console for marketing work and Google Search Console MCP for marketing.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Google Search Console has no declared pricing — check the project's own site. Google Search Console MCP is listed as free. Auth: oauth 2.0. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add google-search-console and acamolese-google-search-console-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Google Search Console has a quality signal of 59/100 (Good) with 1 views, 0 installs and 5 GitHub stars. Google Search Console MCP has 63/100 (Good) with 4 views, 0 installs and 9 GitHub stars.