Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Geoa — Get found in ChatGPT 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.
93/100
tool-list score
13
tools declared
remote
at its publisher
—
calls last 7d
What it does
Check whether ChatGPT, Gemini and Perplexity recommend a business, and get fixes for its website.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http geoa-get-found-in-chatgpt-mcp https://geoa.app/mcp
# 2 — ask your agent for something these tools do
# geoa_verify_claim, geoa_geo_score, geoa_ai_visibility and 10 more
Geoa — Get found in ChatGPT costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GEAll 1 server
geoa1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http geoa-get-found-in-chatgpt-mcp https://geoa.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 X-Client-Key header (Optional geoa connector key (platform.geoa.app, Integrations). Without it, the free tools work.) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
13 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.
Verify a numeric claim against its cited source (geoa's Gate). Fetches the source page and checks mechanically whether the number appears there and whether the source is circular; with a geoa account it also checks SEMANTICALLY whether the source actually supports the claim. Returns a verdict: supported | unsupported | self_referential | unverifiable, plus the matched evidence.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| claim | string | yes | The claim containing the number, e.g. '68% of searches end without a click' |
| source_url | string | no | URL of the source the claim cites |
GEO score for a domain: how ready the site is to be read, understood and cited by AI search engines, measured across 15 technical dimensions. Returns the total score, a grade, and the 3 weakest dimensions (full 15-dimension report requires a geoa account). Results are cached for 6 hours per domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | The domain, e.g. 'example.com' |
Your brand's AI visibility from geoa's stored scans: is your company mentioned when people ask ChatGPT, Claude, Gemini or Perplexity? Returns mention rate per engine, the top visibility gaps, and which competitors are cited instead. Reads stored scan results only (no live engine calls). Requires sign-in to a geoa account.
No parameter schema on file.
Create a source-verified article draft from an AI-visibility gap (e.g. a question from geoa_ai_visibility). The draft is generated with the customer's Brand Brain, source-verified by the Gate and scored by the Coach — and lands as a DRAFT in Content Studio; nothing is published automatically. Requires a sign-in to a geoa account; counts against the plan's article quota.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | The question/topic the draft should answer |
| cited_instead | array | no | Competitor domains cited instead (from geoa_ai_visibility) |
| language | string | no | da (default), no, sv or en |
Your current geoa fix queue: the 5 highest-priority GEO fixes served right now (title, effort, impact, delivery channel) plus how many wait in the backlog and how many are verified done. Every fix is closed by MEASUREMENT, never by claim. Read-only — act on fixes in the geoa dashboard. Requires sign-in to a geoa account.
No parameter schema on file.
Your geoa plan and usage (articles used/remaining this month). Requires sign-in to a geoa account.
No parameter schema on file.
The approved geoa fixes that are NOT yet written into this site's code, for sites built or updated with Claude Code. Each item carries the path (url_pattern), the new value to write, and what geoa measured there before, so you can find the right spot in the repo. A human already approved every item in geoa before it appears here. Read-only. Requires sign-in to a geoa account.
No parameter schema on file.
Report that you have written the given approved fixes into the site and DEPLOYED them. geoa then fetches the public page as an ordinary visitor and confirms the change is really there — a fix is closed by measurement, never by claim, so a report made before the change is live stays unconfirmed. Writes to the customer's geoa account. Requires sign-in to a geoa account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fix_ids | array | yes | The fix_ids you wrote in and deployed (from geoa_pending_fixes) |
| commit | string | no | Optional commit SHA or reference the change landed in |
| deployed_url | string | no | Optional URL where the change is now live |
| tool_version | string | no | Optional client/tool identifier for the report |
| rolled_back | object | no | Optional {fix_id: reason} for changes you reverted instead of keeping |
Content Studio articles that are approved and ready to go into the site: title, body (markdown and HTML), meta description, FAQ, JSON-LD and the EU AI Act disclosure, for sites built or updated with Claude Code. Read-only. Requires sign-in to a geoa account.
No parameter schema on file.
Report that a ready article is now published at a live URL. geoa starts measuring the article's effect on that URL and cross-links the other articles in its cluster to it. Without this, the article stays unpublished in geoa and keeps coming back as ready. Writes to the customer's geoa account. Requires sign-in to a geoa account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| article_id | string | yes | The article id from geoa_ready_articles |
| url | string | yes | The live URL the article is published at (https://…) |
Find B2B prospect companies for a workspace via geoa Radar: discovery by industry+city (or your own seed domains), registry-qualified with Nordic Data (official business registries). Returns a ranked candidate list and a search_id for scoring. Counts against the plan's monthly prospect-search quota. Requires sign-in to a geoa account. Research only — geoa never contacts anyone on your behalf.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| industry | string | no | Industry, e.g. 'vvs' or 'revisor' |
| city | string | no | City (optional) |
| country | string | no | dk (default), no, se or fi |
| seed_domains | array | no | Your own candidate domains instead of discovery |
GEO-score the prospects in a Radar search (search_id from geoa_radar_find_prospects): healthy company + weak AI visibility = highest sales priority. Scoring runs in the background — call again with the same search_id to fetch results. Requires sign-in to a geoa account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search_id | string | yes | Search id from geoa_radar_find_prospects |
Enrich a company domain with verified registry data via Nordic Data (CVR/Brønnøysund/Bolagsverket etc.): registered name, company number, industry code, legal form, status. Counts against the plan's monthly lookup quota. Requires sign-in to a geoa account. Company-level data only — never persons.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Company domain |
| company_name | string | no | Company name if you know it (improves matching) |
| country | string | no | dk (default), no, se, fi … |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Geoa — Get found in ChatGPT 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: —
ATool-list grade · score 93 / 100
Release 1.3.0 · scanned 23 Oct 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digesteecd91e68cb51ff525f6eb2751a16eb68790b52a771d59583bb8105c855b16af
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| geoa_verify_claim | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| geoa_geo_score | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| geoa_ai_visibility | no tags | |
| geoa_draft_from_gap | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| geoa_fix_backlog | no tags | |
| geoa_account_status | no tags | |
| geoa_pending_fixes | no tags | |
| geoa_report_fixes_live | state-write | state-write: declares readOnlyHint: false |
| geoa_ready_articles | no tags | |
| geoa_report_article_published | state-write | state-write: declares readOnlyHint: false |
| geoa_radar_find_prospects | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| geoa_radar_score_prospects | untrusted-inputexternal-sink | untrusted-input: keyword "fetch"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| geoa_radar_enrich | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digesteecd91e68cb51ff5
Scanned2026-10-23
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.3.0.
1.3.0
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 Geoa — Get found in ChatGPT 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.