Google Search Console MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list-propertiesA | Search Console properties the authenticated account can read, with the permission level. Property identifiers come in two forms: sc-domain:example.com (a domain property covering every subdomain and protocol) and URL-prefix like https://example.com/ (exactly that prefix). Call this first and pass the identifier verbatim as |
| queryA | Search Analytics rows for one property: clicks, impressions, CTR and position grouped by up to three of query, page, country, device, date, searchAppearance. Dates are resolved server-side (presets like last_28_days, anchored to the last date with data). Value filters (contains/regex/equals) run inside Search Console; min/max metric filters and non-click sorts run on a top-5000 sample. compare=previous_period or same_period_last_year returns one merged table with server-computed deltas (position_change positive = improved) — never join two windows yourself. Rows are a paginated sample, not an exhaustive export. |
| question-queriesA | Google searches phrased as questions that showed this site — the raw material for FAQ pages and content that answers what people actually ask (including the questions AI features answer). Detection runs inside Search Console via regex filters built from question-prefix lists in 10 languages plus a minimum length. Search Console does not label AI traffic; these are question-shaped candidates. Sorted by impressions by default, since question queries are often shown without a click. |
| opportunitiesA | Ready-made opportunity analyses over the top-5000 rows of a window. low_ctr: rows earning impressions but converting far below the site's own average CTR (threshold = min(5%, max(1%, avg*0.75))). striking_distance: queries ranking positions 4-15 — the cheapest wins. long_tail: conversational queries of 4+ words. cannibalization: queries where two or more of the site's pages compete against each other, with the leading URL. Web search type only. |
| inspect-urlA | Index status of specific URLs via the URL Inspection API: verdict, coverage, robots.txt and indexing state, last crawl, canonical chosen by Google vs declared by the site (mismatches flagged), mobile usability and detected rich results. Pass url for one page or urls for a batch (max 20; requests run 2 at a time). Quota is roughly 600 requests/minute and 2000/day per property — keep batches small. URLs must belong to the property. |
| sitemapsB | Sitemaps of a property: submitted files with their status, errors, warnings and submitted/indexed counts. action=status returns one sitemap (sitemap_url required). submit and delete change the property and only work when the server was started with --enable-writes. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| weekly-report | Wins, losses and actions for the last 7 days versus the week before. |
| content-decay | Pages losing clicks and positions, with the queries that slipped and a refresh plan. |
| striking-distance | Queries at positions 4-15 where one push reaches the top results. |
| cannibalization-check | Queries where several of the site's pages compete, and how to consolidate. |
| questions-to-content | Question-shaped searches turned into an FAQ and content plan (the same questions AI assistants answer). |
| indexing-triage | Sitemap health plus index status of the pages that matter. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly stated distinct purpose, but query, question-queries, and opportunities all operate over the same Search Analytics data. The descriptions differentiate them well (raw rows vs question-shaped candidates vs pre-built analyses), so an agent can mostly tell them apart, though there is latent overlap since query could partially replicate the other two.
All names are lowercase kebab-case, but the pattern is mixed: list-properties, question-queries, and inspect-url follow a verb_noun shape while query, opportunities, and sitemaps are bare nouns. Readable but not a predictable convention.
Six tools is well-scoped for Search Console's surface, with each tool earning its place and none appearing redundant or trivial. No bloat or thinness.
Covers the core GSC lifecycle: property listing, Search Analytics (with comparison and filtering), question mining, opportunity detection, URL inspection, and sitemap status/submit/delete. Minor gaps like property-level administration or authentication/verification ops exist but are typically handled in the UI, so agents can work around them.