AEO & GEO Audit: AI Search Readiness + llms.txt Checker

Answer first: this actor runs an AEO audit / GEO audit on a list of URLs and tells you whether each page can be found, read and quoted by ChatGPT search, Perplexity, Claude and Google AI Overviews / AI Mode. Every page gets an AEO score from 0 to 100, an A-F grade and a ranked fix list. Every domain gets an llms.txt check and a robots.txt check for GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Google-Extended and CCBot. The first 5 pages of every run are free, then $0.008 per page.

Quick facts
Best for	AEO audit, GEO audit, AI search readiness check, llms.txt checker, "does robots.txt block GPTBot / ClaudeBot?", pre-publish checks
Input	A list of page URLs (up to 5,000)
Output	One row per URL: aeoScore, grade, topFixes, aiBotsBlocked, hasLlmsTxt, schema types, answer-first and heading signals
Price	First 5 pages free every run, then $0.008 per page. No start fee. Pages that fail to load are free
Needs	No API keys, no LLM calls, no proxies
Not included	Full-site crawl (use site-seo-aeo-audit), live ChatGPT/Perplexity citation tracking, backlinks

What it checks

• AI crawler access (robots.txt): GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Google-Extended and CCBot
• llms.txt checker: is /llms.txt published on the domain (HTML soft-404 pages don't count)
• Structured data: JSON-LD and microdata types (FAQPage, HowTo, QAPage, Article, Product, Organization…)
• Answer-first content: the first real paragraph is a 15–70 word direct answer
• Question-style H2/H3 headings ("How…", "What…", "…?") and FAQ blocks
• Quotable lists and tables, exactly one H1, meta description length, word count
• Freshness and E-E-A-T: published/modified dates and author signals

Score breakdown (100 points)

Signal	Points
AI crawlers allowed in robots.txt	20
JSON-LD / microdata schema present	12
Answer-first opening paragraph (15–70 words)	12
FAQ / HowTo / QAPage schema or 3+ question headings	10
2+ question-style H2/H3 headings	10
300+ words of content	8
Quotable list or table	7
Meta description 70–170 characters	6
Exactly one H1	5
Published / modified date	4
Author signal	3
/llms.txt published	3

Grades: A 85+, B 70+, C 55+, D 40+, F below 40. Every missed signal becomes a plain-English fix in allFixes, and the first five go in topFixes.

Pricing (pay per event)

• First 5 successfully audited pages in every run are free
• Then $0.008 per page-audited event ($8 per 1,000 pages)
• No actor-start fee. Pages that fail to load (HTTP errors, timeouts) are listed with an error field and not charged
• Duplicate URLs are removed before the run, so you never pay twice for the same URL
• Set a max charge per run and the actor stops cleanly at your limit

Pages audited	You pay*
5	$0.00
25	$0.16 (5 free + 20 × $0.008)
100	$0.76
500	$3.96
1,000	$7.96

*This assumes every page loads. Failed pages are free.

Output (per page)

url, aeoScore, grade, topFixes, allFixes, schemaTypes, aiBotsBlocked, hasLlmsTxt, answerFirst, firstParagraphWords, questionHeadings, h1Count, wordCount, metaDescriptionLength, title. The SUMMARY record in the key-value store holds pagesAudited and averageAeoScore.

Example result

{"url":"https://apify.com","aeoScore":66,"grade":"C","topFixes":["Add an FAQ block with FAQPage schema","Phrase 2+ H2/H3 headings as the questions users ask"],"aiBotsBlocked":[],"hasLlmsTxt":true}

Input example

{
  "urls": [
    "https://example.com/blog/what-is-aeo",
    "https://example.com/pricing",
    "https://example.com/faq"
  ],
  "maxConcurrency": 5
}

Paste up to 5,000 http(s) URLs. maxConcurrency runs 1–20 parallel fetches (default 5).

Who it's for

SEO and AEO/GEO agencies auditing clients, content teams checking pages before publishing, site owners who want to know if robots.txt blocks GPTBot or ClaudeBot, and AI agents running audits through the Apify MCP server.

Use cases

• AEO/GEO audits and client reports
• Pre-publish checks for ChatGPT and AI Overviews citations
• Finding robots.txt rules that block GPTBot, ClaudeBot or PerplexityBot
• Checking whether a domain has an llms.txt file
• Ranking which pages to restructure first
• Batch checks from Claude or Cursor via MCP

How it compares (live Apify Store prices, verified 18 Oct 2026)

List prices on the Apify Free plan, read from the Apify Store API on 18 October 2026. Some actors charge less on higher plans.

Actor	Price	Extra fees	Cost for 100 pages	Focus
cygnix_labs/aeo-readiness-checker (this)	$0.008 / page, first 5 free every run	none	$0.76	Content-level AEO score (answer-first, question headings, FAQ/schema) + 7 AI bots + llms.txt, fix list
jtpalms/seo-ai-readiness-audit	$0.002 / page	$0.003 / site	~$0.20	SEO basics + AI-bot / llms.txt flags
siteverdict/siteverdict-ai-search-readiness	$0.004 / page	$0.03 / site, add-ons extra	~$0.43	Site-level AI-bot matrix, render checks
fayoussef/seo-geo-aeo-audit	$0.0045 / result	none	~$0.45	Combined SEO + GEO + AEO scores, HTML report
dltik/geo-site-audit	$0.01 / page	tiny start fee	~$1.00	AI crawler access, llms.txt, schema
crawlwise/seo-audit-ai-search	$0.01 / page	tiny start fee	~$1.00	SEO basics + AI bot access + llms.txt
alizarin_refrigerator-owner/llms-txt-checker	$0.01 / URL	$0.10 start, $0.02 recommendations	~$1.10+	llms.txt presence and quality
wheaten_steelpan/geo-site-auditor	$0.02 / page	$0.02 start	~$2.02	GEO/AEO crawl + fix list
lofomachines/geo-technical-audit	$0.035 / result	$0.02 start	~$3.52	GEO schema, semantic HTML, E-E-A-T
foxlabs/geo-auditor	$0.04 / page	tiny start fee	~$4.00	GEO technical audit, citability

Honest take. jtpalms, siteverdict and fayoussef are cheaper per page; they mostly grade SEO basics plus bot flags. This actor weights content-level answer-engine signals (answer-first opening, question headings, FAQ/HowTo schema, quotable lists) into one 0-100 score with a fix per missed signal, and spot checks of up to 5 pages cost $0. Among dedicated GEO/AEO page auditors (dltik, crawlwise, wheaten_steelpan, lofomachines, foxlabs at $0.01-0.04) it is the lowest list price.

For AI agents / MCP

When an agent should call this actor: the user gives specific URLs and asks for an AEO or GEO audit, whether pages are ready for ChatGPT / Perplexity / AI Overviews, whether robots.txt blocks GPTBot or ClaudeBot, or whether a site has llms.txt. For a whole website from one URL, call cygnix_labs/site-seo-aeo-audit instead.

Connect the Apify MCP server with only this actor enabled (works in Claude, ChatGPT, Cursor, VS Code, Codex and any MCP client):

https://mcp.apify.com?tools=cygnix_labs/aeo-readiness-checker

Or search for it with the default server: search-actors keywords such as AEO audit, GEO audit, llms.txt, AI search readiness.

Example call-actor input:

{
  "urls": [
    "https://example.com/",
    "https://example.com/pricing",
    "https://example.com/blog/what-is-aeo"
  ],
  "maxConcurrency": 5
}

What to read from the result: each dataset row has url, aeoScore (0-100), grade, topFixes (up to 5, plain English), allFixes, aiBotsBlocked (list of blocked bots), hasLlmsTxt, schemaTypes, answerFirst and questionHeadings. Rows with an error field failed to load and were not charged. The SUMMARY key-value record has pagesAudited and averageAeoScore.

Cost control for agents: Send 5 URLs or fewer for a free check; 100 URLs cost $0.76. Pass maxTotalChargeUsd in callOptions to hard-cap spend. This actor is pay-per-event, so it also works with Apify agentic payments (no Apify account needed for the agent).

Example prompt: "Run an AEO audit on these 10 URLs, tell me which pages block GPTBot or have no llms.txt, and list the top 3 fixes per page."

FAQ

Does it query ChatGPT or Perplexity? No. It audits the on-page and crawl signals those engines rely on, so it is fast and cheap. To measure actual citations, pair it with an AI-visibility tracker.

How is this different from a full SEO audit actor? Full SEO crawlers map the whole site: status codes, redirects, internal links, sometimes Core Web Vitals. This actor scores AI search readiness only: bot access, llms.txt, schema/FAQ, answer-first content and citation structure. Use both if you need technical SEO and AEO.

Which AI bots does it check? GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Google-Extended and CCBot. A bot counts as blocked when its own robots.txt group disallows /, or when it has no group and the * group does, unless there is an Allow: /. Path-level rules (e.g. Disallow: /blog/) are not counted as a full block.

Does it check the whole site? It audits the URLs you give it. robots.txt and /llms.txt are fetched once per domain and reused for every page on that domain.

JavaScript-heavy sites? It reads server-rendered HTML, the same way most AI crawlers do. Client-only SPAs may score low until their content is SSR/prerendered.

What if a page is down or blocks the request? It is still listed, with an error field and a score of 0, and you are not charged for it.

Can I cap my spend? Yes. Set a maximum charge per run in the run options, and the actor stops cleanly when it hits the limit.

Is there a free allowance? Yes. The first 5 successfully audited pages in every run are free, and only pages after that are charged.

What is the difference between AEO and GEO? AEO (answer engine optimization) is about pages being picked as the direct answer; GEO (generative engine optimization) is about being cited by generative AI search such as ChatGPT, Perplexity and AI Overviews. The checks overlap almost entirely: crawler access, extractable answers, structure and trust signals. This actor scores both with one 0-100 AEO score.

Is llms.txt worth it? It is cheap to publish and coding agents read it, but studies in 2026 show AI search crawlers rarely request it. That is why it carries only 3 of 100 points here, while AI crawler access in robots.txt carries 20.

Integrations

Run it via the Apify API, schedule weekly runs, or send results to Google Sheets, Make, Zapier, n8n, Slack or webhooks.

Changelog

• 0.1.8 (2026-10-18): README and Store text rewritten answer-first: AEO audit / GEO audit / llms.txt terms, quick facts, comparison re-verified against 10 named actors on 18 Oct 2026, "For AI agents / MCP" section with example input, AEO vs GEO and llms.txt FAQ. Price unchanged ($0.008/page, first 5 free).
• 0.1.7 (2026-10-16): Named Store comparison, bot-blocking rule explained, default memory 1 GB.
• 0.1.6 (2026-10-16): Cost table, score breakdown, FAQ, MCP link. Price $0.008 per page-audited, first 5 pages free.

More SEO and AEO tools by Cygnix Labs

• Website SEO Audit + AEO/GEO Checker (full-site crawl)
• Internal Link Audit & Orphan Page Finder
• Content Decay Audit (Search Console)
• Keyword Cannibalization Checker (Search Console)
• Keyword Clustering + Content Briefs
• Search Intent Classifier
• Free local SEO MCP server: cygnix-seo-mcp (npx -y cygnix-seo-mcp)

Questions or a feature request? Open an issue on this actor's Issues tab. We answer within 24 hours.