Platform · Connect

Your report, inside the assistant

AEOSearch runs an MCP server. Sign in to it from Claude or ChatGPT, or hand a token to Claude Code or Cursor, and ask it what the dashboard would show you: the questions you lost, who won them, and what the answers cited.

What It Reads

Each tool below runs the same computation the dashboard renders over your stored answers. Ask in your own words; the assistant picks the tool.

get_overview_metricsThe headline numbers: visibility, sentiment, average position and share of AI voice, under any filter
compare_runsThis window against the last one, so a delta can be stated, and a plain answer when there is no prior run
get_question_detailOne question: its visibility, which engines answered it, which brands those answers named, and how many stored answers back that up
list_lost_questionsEvery question you are losing, with sample counts so a failed call never reads as absence
get_sources_summaryThe domains the answers cite most, labelled yours, competitor or third-party
get_remediation_queueThe Fixes queue with status and priority, on the plans that include Fixes
find_answer_passagesQuoted passages of what the engines actually answered, narrowed by question or phrase
get_site_findingsThe latest site crawl: health, critical pages and every check that found a problem
get_terminology_sweepPages of your own that use a word your approved profile says you avoid, counted per page by section
get_keyword_positionsTracked keywords with the latest stored position per source and its date
get_readiness_checksAnswer Readiness pass, warn and fail per check, and the checks that could not run
get_pulse_movesWhat moved on the daily pulse and what is only the line wandering on its own, per assistant and overall, with the rule that decided it
list_loop_runsThe loops on this property and their last three runs: proposed, approved, applied, the receipt ids, or the refusal sentence
list_propertiesEvery property the account owns, with the id the other tools take and the latest complete run
get_report_summaryThe latest report in one screen: the rates with their intervals, each engine's model and grounding, the four cover disclosures, won and lost, top sources
get_pulseThe daily pulse as day rows: mention rate, share of AI voice and the answers behind each day, for the last N days
get_ad_readbackThe ad platform's own daily numbers for the launched ads: spend, impressions, clicks, purchases, value, and the totals
get_studio_planThe Studio band and this month's meter: credits used against the ceiling, render dollars spent, and the constants a piece is priced against

The headline tool reports grounding per engine, and the server tells the assistant at connect time to check it before presenting a number as what that assistant answers today. A failed engine call is never counted as your absence: failed samples leave every metric, and the counts travel with the answer so the assistant can say how many samples it is standing on.

Sign In From Claude or ChatGPT

Add the server as a custom connector in Claude or in ChatGPT, at the www address:

https://www.aeosearch.io/api/mcp

The assistant sends you to AEOSearch to sign in, then to a consent page where you allow it. No token is copied anywhere. The connection holds one scope, mcp:read, and 60 calls per clock hour. Use the address exactly as written: the bare domain redirects, and Claude drops the sign-in across a redirect.

What the connection may do is checked against your account on every call. On a monthly custom report, Track, Grow or Command account it gets every tool above. On any other account it gets one tool, run_free_report, which starts the free report the website gives away, four questions on ChatGPT and Gemini, once per account. Once the account owns a property, Settings, then Connected apps, lists each connection, and Disconnect ends it on its next call.

Or Connect With a Token

1. Mint a token
Settings, then API tokens, on any a monthly custom report, Track, Grow or Command account. The token is shown once. It reads every property created under your sign-in email, it never expires, and revoking it is the only way to end it. Up to 5 live at a time, 60 calls each per clock hour.

2. Add the server

Claude Code, one line:

claude mcp add --transport http aeosearch https://www.aeosearch.io/api/mcp \
  --header "Authorization: Bearer aeo_…"

Cursor, or any client that reads a JSON config with headers:

{
  "mcpServers": {
    "aeosearch": {
      "url": "https://www.aeosearch.io/api/mcp",
      "headers": { "Authorization": "Bearer aeo_…" }
    }
  }
}

Anything else that speaks JSON-RPC can post straight to the endpoint with the same header. The server answers initialize, tools/list and tools/call, one call per request.

3. Ask
“Which questions did we lose on ChatGPT last run, and which domains did the winning answers cite?” If the account owns more than one property, name it, or pass property in the call: the error lists your property ids.

The Free Scan, No Account

A second server needs no account and no token. Any assistant can add it:

https://www.aeosearch.io/api/mcp/public

It has one tool, scan_site: the free Agent Readiness Scan, the same one the website runs. It reads one public site and reports which readiness checks pass, warn or fail, and the top fixes. It never says whether an assistant names the brand, because that takes a measurement of real answers, which a scan does not run. Once a site is scanned, asking again inside 24 hours returns the stored result.

What It Never Does

Nothing a token can reach changes anything. The Fixes queue moves only from the dashboard, on purpose: an assistant that can quietly rewrite your remediation list is the kind of thing you find out about later, so we built the read side first and stopped there.

A signed-in connection reads the same way. The one thing it can start is your account's free report, once, and that costs you nothing.

Start with the free scorecard.

Add the connector in Claude or ChatGPT and sign in, or mint a token from Settings. The first question takes about a minute.

Get your scorecard

$0 to start · no card required · every number traces to a stored answer