geoa
Registry code: b3a0a2846c990a99
Check whether ChatGPT, Gemini and Perplexity recommend a business, and get fixes for its website.
from a public catalogue that lists it, not from the operator
- endpoint
- https://geoa.app/mcp
- protocol
- streamable-http ·2025-03-26
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is geoa live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is geoa free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does geoa have?
- 13 tools: geoa_geo_score, geoa_draft_from_gap, geoa_pending_fixes, geoa_report_fixes_live, geoa_ready_articles, geoa_report_article_published, geoa_radar_find_prospects, geoa_radar_score_prospects, ….
- Is geoa safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 13 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
geoa_ai_visibility auth-required 1h ago
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 a connector key.
{ "type": "object", "properties": {} }arguments 4 linesgeoa_geo_score unknown never probed
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.
{ "type": "object", "required": [ "domain" ], "properties": { "domain": { "type": "string", "description": "The domain, e.g. 'example.com'" } } }arguments 12 linesgeoa_draft_from_gap unknown never probed
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 connector key; counts against the plan's article quota.
{ "type": "object", "required": [ "question" ], "properties": { "language": { "type": "string", "description": "da (default), no, sv or en" }, "question": { "type": "string", "description": "The question/topic the draft should answer" }, "cited_instead": { "type": "array", "items": { "type": "string" }, "description": "Competitor domains cited instead (from geoa_ai_visibility)" } } }arguments 23 linesgeoa_pending_fixes unknown never probed
The approved geoa fixes that are NOT yet written into this site's code — use this when you build or update the customer's website 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; they are changes to make, not suggestions to weigh. Read-only. Requires a connector key.
{ "type": "object", "properties": {} }arguments 4 linesgeoa_report_fixes_live unknown never probed
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 call this only after the change is actually live. Writes to the customer's geoa account. Requires a connector key.
{ "type": "object", "required": [ "fix_ids" ], "properties": { "commit": { "type": "string", "description": "Optional commit SHA or reference the change landed in" }, "fix_ids": { "type": "array", "items": { "type": "string" }, "description": "The fix_ids you wrote in and deployed (from geoa_pending_fixes)" }, "rolled_back": { "type": "object", "description": "Optional {fix_id: reason} for changes you reverted instead of keeping" }, "deployed_url": { "type": "string", "description": "Optional URL where the change is now live" }, "tool_version": { "type": "string", "description": "Optional client/tool identifier for the report" } } }arguments 31 linesgeoa_ready_articles unknown never probed
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. Use this when you build or update the customer's website with Claude Code. Read-only. Requires a connector key.
{ "type": "object", "properties": {} }arguments 4 linesgeoa_report_article_published unknown never probed
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 a connector key.
{ "type": "object", "required": [ "article_id", "url" ], "properties": { "url": { "type": "string", "description": "The live URL the article is published at (https://…)" }, "article_id": { "type": "string", "description": "The article id from geoa_ready_articles" } } }arguments 17 linesgeoa_radar_find_prospects unknown never probed
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 a connector key. Research only — geoa never contacts anyone on your behalf.
{ "type": "object", "properties": { "city": { "type": "string", "description": "City (optional)" }, "country": { "type": "string", "description": "dk (default), no, se or fi" }, "industry": { "type": "string", "description": "Industry, e.g. 'vvs' or 'revisor'" }, "seed_domains": { "type": "array", "items": { "type": "string" }, "description": "Your own candidate domains instead of discovery" } } }arguments 24 linesgeoa_radar_score_prospects unknown never probed
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 a connector key.
{ "type": "object", "required": [ "search_id" ], "properties": { "search_id": { "type": "string", "description": "Search id from geoa_radar_find_prospects" } } }arguments 12 linesgeoa_radar_enrich unknown never probed
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 a connector key. Company-level data only — never persons.
{ "type": "object", "required": [ "domain" ], "properties": { "domain": { "type": "string", "description": "Company domain" }, "country": { "type": "string", "description": "dk (default), no, se, fi …" }, "company_name": { "type": "string", "description": "Company name if you know it (improves matching)" } } }arguments 20 linesgeoa_verify_claim unknown never probed
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.
{ "type": "object", "required": [ "claim" ], "properties": { "claim": { "type": "string", "description": "The claim containing the number, e.g. '68% of searches end without a click'" }, "source_url": { "type": "string", "description": "URL of the source the claim cites" } } }arguments 16 linesgeoa_account_status unknown 1h ago
Your geoa plan and usage (articles used/remaining this month). Requires a connector key.
{ "type": "object", "properties": {} }arguments 4 linesgeoa_fix_backlog unknown 1h ago
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 a connector key.
{ "type": "object", "properties": {} }arguments 4 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idb3a0a2846c990a99.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/b3a0a2846c990a99/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/b3a0a2846c990a99?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.