Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Google Search Console is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
19
tools declared
local
runs on your machine
—
downloads a day
What it does
Search Console analytics, hourly data, URL inspection and sitemaps, with guards for API quirks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user onlymoein-google-search-console-mcp '--' uvx open-gsc-mcp
# 2 — ask your agent for something these tools do
# query_search_analytics, list_search_appearances, query_search_appearance and 16 more
Google Search Console costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ONAll 1 server
onlymoein1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Google Search Console as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user onlymoein-google-search-console-mcp '--' uvx open-gsc-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take GSC_SERVICE_ACCOUNT_FILE (Absolute path to a service account JSON key. Leave unset to use the OAuth login from `open-gsc-mcp auth login`.), GSC_ENABLE_WRITES (Set to 1 to enable submit/delete sitemap and add/delete site tools.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Clicks, impressions, CTR and average position from the Performance report, grouped by dimensions and filtered. Rows are sorted by clicks. Invalid combinations are rejected with an explanation before Google is called. For one surface at a time, the query_discover/image/video/news_analytics tools…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | no | — | |
| search_type | no | web, image, video, news (the News tab), discover or googleNews. | |
| filters | no | — | |
| data_state | no | — | |
| aggregation_type | no | — | |
| row_limit | no | — | |
| start_row | no | — |
Step one: list the search appearances (rich results and other result features, such as VIDEO or REVIEW_SNIPPET) the property had, with clicks and impressions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | no | — | |
| end_date | no | — | |
| search_type | no | — | |
| data_state | no | — |
Step two: performance of one search appearance, broken down by query, page, country, device or date. Get the appearance name from list_search_appearances.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| appearance | string | yes | Exact appearance name from list_search_appearances, such as VIDEO or REVIEW_SNIPPET. |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | array | no | Break the appearance down by these. Omit for ['query'] (['page'] for Discover and Google News). |
| search_type | no | — | |
| filters | array | no | Extra filters, combined with AND with the appearance. |
| data_state | no | — | |
| row_limit | no | — | |
| start_row | no | — |
Compare search performance between two periods of equal length: totals plus a per-key breakdown with absolute and percent changes. Position change is negative when ranking improved.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| current_start | string | no | First day of the period to analyze, YYYY-MM-DD (Pacific Time). |
| current_end | string | no | Last day of the period to analyze. Defaults to 3 days ago, the last day that is usually final. |
| previous_start | string | no | First day of the baseline. Defaults to the period just before. |
| previous_end | string | no | Last day of the baseline; same length as current. |
| dimensions | array | no | Compare per value of these. Omit for ['query']; [] for totals only. |
| search_type | no | — | |
| filters | array | no | Filters, combined with AND. |
| data_state | no | Defaults to 'final': fresh, still-changing data in the current period would read as a decline against a complete baseline. | |
| sort_by | no | — | |
| row_limit | integer | no | Rows to return. |
| fetch_limit | integer | no | Top rows fetched per period before joining. |
Search performance broken down by hour (Pacific Time) for the last ~10 days. Use it to spot same-day spikes or compare today with the same day last week. The most recent hours are incomplete; first_incomplete_hour says where that starts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | string | no | First day, YYYY-MM-DD in Pacific Time, within the last {HOURLY_DAYS} days. Defaults to {DEFAULT_HOURLY_DAYS - 1} days ago. |
| end_date | string | no | Last day, YYYY-MM-DD in Pacific Time. Defaults to today. |
| dimensions | array | no | Extra grouping besides the hour. Omit for hourly totals. |
| search_type | no | — | |
| filters | array | no | Filters, combined with AND. |
| row_limit | no | — | |
| start_row | no | — |
Google's index status for one URL: whether it is indexed and why not, last crawl, canonical chosen by Google versus declared, robots.txt and fetch state, sitemaps and rich results. This is Google's indexed view, not a live test of the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| url | string | yes | Full URL of the page, inside the property. |
| language_code | no | — |
Inspect up to 50 URLs concurrently and summarize their index verdicts. Failures are reported per URL; if the daily quota runs out, the remaining URLs are skipped and listed so you can retry them later.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| urls | array | yes | 1-{MAX_BATCH} page URLs. |
| language_code | no | — |
List submitted sitemaps with their status: last submitted and downloaded, errors, warnings, whether processing is pending, and URL counts by content type.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| sitemap_index | string | no | Only list the sitemaps inside this sitemap index URL. |
Status of one submitted sitemap.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| sitemap_url | yes | — |
Submit (or resubmit) a sitemap so Google fetches it. Safe to repeat.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| sitemap_url | yes | — |
Remove a sitemap from Search Console. Google may still know the URLs in it, and the file itself is not touched. Confirm with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| sitemap_url | yes | — |
List every Search Console property this account can access, with its exact site_url and permission level. Call this first: every other tool needs a site_url.
No parameter schema on file.
Get one property's exact site_url, type and this account's permission level.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — |
Add a property to this account. It starts unverified: ownership must be verified in the Search Console web interface before any data is available.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | string | yes | New property: 'sc-domain:example.com' or a URL prefix such as 'https://www.example.com/'. |
Remove a property from this account. This removes access for this account only;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | string | yes | The property's exact site_url, as listed by list_sites. |
Google Discover performance: clicks, impressions and CTR by page, country or date.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | array | no | Group rows by these. Omit for ['page']; [] for totals. |
| filters | array | no | Filters, combined with AND. |
| data_state | no | — | |
| aggregation_type | no | — | |
| row_limit | no | — | |
| start_row | no | — |
Performance in Google Images and the Images tab of Search: clicks, impressions, CTR and average position within image results, by query, page, country, device or date.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | no | — | |
| filters | no | — | |
| data_state | no | — | |
| aggregation_type | no | — | |
| row_limit | no | — | |
| start_row | no | — |
Performance in the Videos tab of Google Search: clicks, impressions, CTR and average position, by query, page, country, device or date. Video results shown on the main web results are counted under web search, not here.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | no | — | |
| filters | no | — | |
| data_state | no | — | |
| aggregation_type | no | — | |
| row_limit | no | — | |
| start_row | no | — |
News performance: Google News (news.google.com and the app) or the News tab in Google Search. Clicks, impressions and CTR by page, country, device or date; the News tab also has queries and average position.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site_url | yes | — | |
| source | string | no | 'google_news': news.google.com and the Google News app (no queries, no position). 'news_tab': the News tab in Google Search. |
| start_date | no | — | |
| end_date | no | — | |
| dimensions | array | no | Group rows by these. Omit for ['page'] (google_news) or ['query'] (news_tab); [] for totals. google_news has no query. |
| filters | no | — | |
| data_state | no | — | |
| aggregation_type | no | 'auto' is right almost always. google_news is aggregated by page (no byProperty); byNewsShowcasePanel needs a searchAppearance equals NEWS_SHOWCASE filter and google_news. | |
| row_limit | no | — | |
| start_row | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Google Search Console or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 1.1.0 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 3 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digestee9dc23eba9451fbd00e3357ee8041f79e6a9a5a33c14ad464666f194c07372b
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
2 of the 19 recovered tools are registered only when not deps.settings.enable_writes is false (src/gsc_mcp/tools/sitemaps.py:60) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 15.
2 of the 19 recovered tools are registered only when not deps.settings.enable_writes is false (src/gsc_mcp/tools/sites.py:56) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 15.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
15 tools are registered unconditionally · (1) 2 more only when not deps.settings.enable_writes is false (src/gsc_mcp/tools/sitemaps.py:60) · (2) 2 more only when not deps.settings.enable_writes is false (src/gsc_mcp/tools/sites.py:56) — typically when a key or option is configured. All 19 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| query_search_analytics | no tags | |
| list_search_appearances | no tags | |
| query_search_appearance | no tags | |
| compare_periods | no tags | |
| query_hourly_analytics | no tags | |
| inspect_url | untrusted-input | untrusted-input: keyword "fetch", parameter "url" with "fetch" in the description |
| batch_inspect_urls | no tags | |
| list_sitemaps | no tags | |
| get_sitemap | no tags | |
| submit_sitemap conditional (1) | no tags | |
| delete_sitemap conditional (1) | no tags | |
| list_sites | no tags | |
| get_site | no tags | |
| add_site conditional (2) | no tags | |
| delete_site conditional (2) | no tags | |
| query_discover_analytics | no tags | |
| query_image_analytics | no tags | |
| query_video_analytics | untrusted-input | untrusted-input: keyword "web_search" |
| query_news_analytics | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestee9dc23eba9451fb
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.1.0. Pin a release below and the command asks for exactly that one.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Google Search Console can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.