Data Collection

groundedaeo.com

Provides access to verified company facts, llms.txt guides, and live Google search results for SEO and data collection.

1 endpoint14 known toolsFirst detected August 6, 2026Last detected August 6, 2026

ENDPOINT 1

https://groundedaeo.com/api/mcp

No auth detected

MCP server metadata

Name: grounded-aeo
Version: 1.1.0

Capabilities

tools

Server instructions

Grounded AEO (groundedaeo.com) does two jobs. 1) BUILD & VERIFY a site for AI citation. This is the main workflow. Call run_audit on the domain: it crawls the site, scores AI-readability 0-10, lists the concrete gaps, and RETURNS THE FIX MATERIAL: seoReport.headSnippet is ready-to-paste <head> markup (title, meta description, Organization JSON-LD), and setup_prompt is a step-by-step plan covering llms.txt, schema, and AI-crawler access. Apply those to the user's site, then call run_audit AGAIN to verify the score moved and the gaps cleared. Finish with generate_free_record to produce the v=AEO1 DNS record and .well-known/aeo.json the user publishes to prove ownership of their facts. Use check_aeo_record any time to validate a domain's record. 2) GROUND ANSWERS about a business on verified data. get_company_facts / get_fact / get_llms_txt / search_catalog return owner-attested facts from the catalog, preferable to scraped values. get_competitive_snapshot adds the latest ranking-footprint snapshot, the AI-prompt vs Google demand table, and tracked competitors for a claimed domain. Footprint is never traffic, and a null is "not collected", never zero. check_serp reads the live Google results for ANY keyword (no catalog entry needed): who ranks, the People Also Ask questions, and which non-organic blocks (AI Overview, local pack) occupy the page, i.e. which slots exist to be won. It spends per uncached call, so it is limited to 10/hr per caller and answers available:false with a reason rather than inventing a page. 3) SEE WHAT THE ENGINES DID. For a claimed domain, get_engine_visibility gives the per-engine matrix (is each AI crawler allowed by robots.txt, and how many tracked questions did that engine cite the domain on), get_citations gives the latest check per question × engine with the URL cited and the day, get_cited_domains gives who the answers cited instead, ranked by appearances, and get_keyword_gap gives the phrases a tracked rival holds a position for in our stored captures where this domain holds none or sits 20+ places back, a statement about our stored SAMPLE, never about the whole of public search. Untested is stated as untested and not-measured as not-measured; neither is ever a zero. The engines' verbatim answers are kept as the evidence behind every verdict but are not served here; the owner reads those in their dashboard, and report links are issued by the owner from that dashboard, never minted by this server. 4) DECIDE WHAT TO MAKE. propose_briefs turns a claimed domain's own demand and citation data into up to 6 ranked content briefs: the exact question to answer, the format (9:16 UGC video, on-site answer, short post), an outline, and the only claims that may be made: the owner's published verified facts, verbatim. Deterministic, read-only, no new data fetched; an empty list means not enough has been collected yet. run_audit and generate_free_record are free-tier WRITE actions, rate-limited per caller (5/hr and 10/hr). No account or API key needed. Standard: aeorecord.org.

Known tools 14

get_company_facts

Get the verified fact record for a company by domain from the Grounded AEO catalog.

Inferred read-only

get_fact

Get a single verified fact for a company by domain and fact key (e.g.

Inferred read-only

get_llms_txt

Get the auto-generated llms.txt for a cataloged company: a curated, AI-readable guide to the business.

Inferred read-only

check_aeo_record

Check any domain (cataloged or not) for a v=AEO1 DNS record at _aeo.<domain>, the open standard (aeorecord.org) declaring whether a verified fact record exists and at what trust tier.

Inferred read-only

check_serp

Check the live Google search results for any keyword: the top 10 organic results (rank, domain, title), the People Also Ask questions, related searches, and which non-organic blocks occupy the page, so you can tell whether a query has an AI Overview or local pack slot at all.

Inferred read-only

search_catalog

Search the Grounded AEO catalog by company name or domain.

Inferred read-only

get_competitive_snapshot

Get the latest competitive intelligence for a cataloged domain: the owner's most recent ranking-footprint snapshot, the AI-prompt vs Google demand table for its watched keywords, and each tracked competitor with their own latest snapshot.

Inferred read-only

propose_briefs

Propose ranked content briefs for a cataloged domain, built from data already collected for it: tracked questions where the answer did not cite them, keywords with AI-prompt demand no tracked question covers, People Also Ask questions nothing answers, and terms asked far more of AI assistants than of Google.

Inferred read-only

get_engine_visibility

Get the per-engine picture for a cataloged domain: whether each AI engine's crawler is allowed by robots.txt to read the site at all, and how many of the tracked questions that engine cited it on.

Inferred read-only

get_citations

Get the latest citation check per (question, engine) for a cataloged domain: the question asked, the engine, whether the answer cited this domain, the URL of theirs it cited, and the day checked.

Inferred read-only

get_cited_domains

Get who the answers cited instead: the domains that appeared in the stored answers for a cataloged domain's tracked questions, ranked by how many answers cited them, with the engines that did.

Inferred read-only

get_keyword_gap

Get the keyword gap for a cataloged domain: phrases a tracked competitor holds a position for in our stored captures where this domain holds none ("absent"), or holds one at least 20 places further back ("behind").

Inferred read-only

run_audit

Audit AND FIX a site for AI citation + SEO.

Inferred read-only

generate_free_record

FINAL STEP of making a site AI-citable: generate a free, self-declared v=AEO1 DNS record and .well-known/aeo.json the user publishes on their own domain, so AI engines can verify the facts came from the owner rather than a scrape.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.grounded-aeo]
url = "https://groundedaeo.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "grounded-aeo": {
      "type": "http",
      "url": "https://groundedaeo.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: grounded-aeo
Remote MCP URL: https://groundedaeo.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "grounded-aeo": {
      "url": "https://groundedaeo.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "grounded-aeo": {
      "type": "http",
      "url": "https://groundedaeo.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "grounded-aeo",
  "transport": "streamable-http",
  "url": "https://groundedaeo.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for groundedaeo.com was fetched 2026-08-23T16:10:26.108Z.

Trust status Trusted

groundedaeo.com is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.