Pricing

Rating

Developer

Actor stats

Categories

Share

👁 GEO Auditor — AI Search Readiness & Citability Audit

GEO Auditor — AI Search Readiness & Citability Audit

👁 GEO / AEO
 👁 Score
 👁 AI crawlers
 👁 Deterministic
 👁 MCP

Is your website ready to be found, read and cited by AI search — ChatGPT, Perplexity, Gemini and Claude?

AI answer engines don't rank ten blue links — they read a handful of pages, pull the most extractable facts, and cite a few sources. If an AI crawler can't reach your pages, can't parse your content, or can't trust your structure, you simply won't appear in the answer. This is the technical layer of GEO (Generative Engine Optimization) — and most sites are quietly failing it.

This Actor crawls your site exactly the way an AI crawler sees it (raw HTML, no JavaScript rendering), scores its AI-readiness 0–100, and hands you a prioritized, evidence-backed fix list.

Why this audit is different

Most "GEO audits" are shallow checklists. This one actually crawls your pages and scores the signals that decide AI citation — and it's 100% deterministic (no LLM guesswork, no per-run AI cost, no proxy):

Pairs with AI Brand Monitor: that tells you whether AI mentions your brand; this tells you why — and exactly what to fix.

What it checks (5 weighted dimensions)

1. AI-crawler access — 25% — does robots.txt let the crawlers that power AI answers in? Blocking OAI-SearchBot, PerplexityBot, ChatGPT-User, Claude-SearchBot, Googlebot or Bingbot makes you invisible in those answers. (Training crawlers like GPTBot/CCBot are reported separately — blocking those is a valid privacy choice, not penalized.)
2. Structured data — 20% — JSON-LD presence & useful schema types (Organization, Article, Product, FAQPage, BreadcrumbList…). AI engines lean on this to understand and cite you.
3. Content extractability — 30% (highest weight) — heading structure, content depth, text-to-HTML ratio, lists/tables, and a JavaScript-render check (if your content only appears after JS, AI crawlers see an empty page).
4. Speed — 15% — fast, light pages are far more likely to be cited.
5. Trust & freshness — 10% — published/modified dates, author/Organization schema, canonical tags.

Output

Per page: GEO score + band, word count, JSON-LD schema types, heading outline, JS-render risk, canonical & date signals, and the page's top issues.

Site scorecard (summary): overall GEO Readiness Index (0–100), AI-crawler access summary, the list of any blocked AI-search bots, per-dimension scores, and a prioritized fix list ordered by impact.

Quick start

1. Enter your website URL.
2. Set max pages to audit (1 = just that page).
3. Run it.

No API keys, no proxy, no setup.

{
"websiteUrl":"https://www.yoursite.com",
"maxPages":10
}

Use it as an MCP tool (inside any AI agent)

Hosted: https://mcp.apify.com?tools=foxlabs/geo-auditor Self-hosted (Claude Desktop, Cursor, Cline):

$npx @apify/actors-mcp-server --tools foxlabs/geo-auditor

Who it's for

• SEO / GEO agencies — ship clients a technical AI-readiness audit + fix roadmap (recurring).
• In-house SEO / web teams — find why you're not showing up in AI answers, then fix it.
• Founders — a 2-minute check on whether AI search can even see your site.

Note on scope: this is a technical/structural audit (crawlability, structure, schema, speed). It does not render JavaScript — by design, because most AI crawlers don't either, so a JS-only page genuinely is invisible to them.

Changelog

0.1.5 — 2026-06-04

• Structured-data detection now catches nested JSON-LD @types (e.g. SearchAction inside potentialAction).
• Removed the "add llms.txt" suggestion from the fix list: as of 2026, AI-search crawlers don't fetch /llms.txt and it doesn't measurably improve citation, so recommending it as a fix would be misleading. The presence of llms.txt is still reported as an informational field.

0.1.2 — 2026-06-01

• Reachability: automatic www↔non-www fallback; optional residential proxy for WAF-protected sites; browser User-Agent; graceful per-page skip so one bad page never fails the run.

0.1.0 — 2026-06-01

• Initial release: deterministic GEO / AI-search readiness audit — 0–100 score across 5 weighted dimensions (AI-crawler access, structured data, content extractability, speed, trust) with a prioritized, evidence-backed fix list.

Built by foXLabs.