AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini, Copilot & Google AI Overview

Does ChatGPT recommend your brand?

Track AI Brand Visibility across 5 AI search engines (ChatGPT, Perplexity, Microsoft Copilot, Google AI Overview, Google AI Mode) — and optionally Gemini + Grok — for $0.30 per query. Each query expands into ~20 real AI checks with ground-truth validated results. No subscription, no API keys, no monthly contracts. Co-designed with a senior SEO/GEO analyst. Callable as an MCP tool today from Claude Desktop, Claude Code, Cursor, VS Code, n8n and any AI agent — through the Apify MCP server, no extra setup.

A Profound / Otterly / AthenaHQ alternative — without the $29–$489/month subscription. $0.30/query, pay-as-you-go, 60–160× cheaper per AI datapoint than Otterly Lite.

---

What is AI Brand Visibility?

AI Brand Visibility measures how often, how prominently, and how consistently your brand appears in answers from generative AI search engines — ChatGPT, Perplexity, Google AI Overview, Google AI Mode, Microsoft Copilot, Gemini — when buyers ask the questions that move their decision. It is the AI-search equivalent of organic SEO ranking.

The field has three near-synonyms:

• GEO (Generative Engine Optimization) — optimising for the answer the AI generates.
• AEO (Answer Engine Optimization) — optimising for the question-answer pair.
• AI Search Optimization — the umbrella term covering both.

This actor reports all three views in one $0.30 run, with ground-truth validation that catches the 5.6× hallucination inflation other AI Brand Monitoring tools quietly pass through.

---

⚡ Quick Start — try in 30 seconds

Click Try for free above. The default input runs a real scan against Apify as the brand — you'll see actual JSON output, ground-truth validated, in 3 minutes.

Then change brand to your own:

{
  "brand": "HubSpot",
  "category": "CRM software",
  "competitors": ["Salesforce", "Pipedrive", "Zoho CRM"],
  "language": "us",
  "queries": [
    "best CRM for marketing agencies",
    "HubSpot vs Salesforce for small business",
    "AI features in HubSpot CRM"
  ]
}

Sample output (real scan, trimmed):

{
  "brand": "HubSpot",
  "summary": {
    "ais": 74.6,
    "mention_rate": 89.6,
    "share_of_voice": 14.4,
    "consistency_score": 46.7,
    "avg_position": 2.0,
    "top3_rate_pct": 86.8,
    "sentiment_positive_pct": 39.7,
    "dominant_framing": "leader",
    "ground_truth_validated": true
  },
  "competitors": [/* same metrics for each tracked competitor */],
  "per_platform_per_brand": [/* full engine × brand matrix */],
  "per_query": [/* every (query × engine) cell with framing, position, gap class */],
  "top_cited_domains": [/* domains AI engines trust on your topic */]
}

3 queries = ~$0.90 on the Free Apify tier, ~$0.54 on Gold (40% volume discount).

---

💰 Why $0.30 (and not $29–$489/month subscriptions)

	Otterly Lite	AthenaHQ Self-Serve	DoesAIKnow (this actor)
Entry price	$29/mo (annual contract)	$95–$295/mo	$0.30/query, no subscription
Engines included	4 (Gemini + AI Mode are $9/mo add-ons each)	8	5 default + Gemini/Grok on demand
Cost per AI datapoint	$1.93	~$0.08	$0.012 – $0.020
Ground-truth validated	Marketing copy yes, reality varies	Not advertised	Yes — 3-layer markdown gating, documented
MCP tool (Claude / Cursor / agents)	No	No	Yes — live now via the Apify MCP server
Minimum commitment	Monthly subscription	Monthly subscription	3 queries ($0.90)

Otterly/AthenaHQ pricing verified 2026-05-15. Per-datapoint math: $0.30/query × ~20 checks = $0.015/check ($0.011 with all 7 engines). 60–160× cheaper than Otterly Lite ($1.93/dp). Even AthenaHQ's $0.08/credit is 4–8× more.

---

🎯 What this AI Brand Visibility Tracker does

AI search is replacing classic Google. When a buyer asks ChatGPT, Perplexity, Gemini, or Google AI Overview "what's the best CRM for a marketing agency?" — does your brand appear? In what position? With what framing (leader, alternative, just-mentioned)? How do competitors perform on the same queries on the same engines?

Most AI-visibility tools give you one prompt on one or two engines and call it a day. That's a lucky-guess audit. This actor covers buyer intent. One query you type becomes ~4 semantically related variants (sourced from Google's People-Also-Ask and related searches), each run across 5 engines — so one query buys you ~20 validated AI data points instead of one.

On top of that, every metric in the output is ground-truth validated against the raw AI response text. Brand extraction LLMs routinely hallucinate up to 5.6× more mentions than actually appear. We catch that inflation at three layers before it touches your numbers.

---

💸 Pricing detail — flat $0.30/query, automatic volume discount via Apify tier

Apify tier	Price per query	Discount
Free	$0.30	—
Bronze (Starter)	$0.27	−10%
Silver (Scale)	$0.23	−23%
Gold (Business)	$0.18	−40%

Minimum order: 3 queries ($0.90 on Free tier, $0.54 on Gold).

What you actually get for $0.30

1 query you typed
   └── 3–5 semantically related variants (People-Also-Ask + related searches)
        └── × 5 AI engines (ChatGPT, Perplexity, Gemini, Copilot, Google AI Overview)
              └── = ~20 real AI responses
                    └── Each validated against the raw markdown (3-layer ground truth)
                          └── Scored, classified, cross-compared with competitors

~20 real AI checks for $0.30. At the Gold tier that's $0.007–$0.012 per datapoint.

Sample costs

Scenario	Queries	Free tier	Gold tier
Quick brand check	3	$0.90	$0.54
Monthly brand scan	10	$3.00	$1.80
Deep competitive audit	30	$9.00	$5.40
Agency client report (5 clients)	100	$30.00	$12.00
Heavy power user	500	$150.00	$60.00

---

🤖 Use it from Claude, Cursor or any AI agent — MCP, live today

Most AI Brand Visibility tools think their customer is a marketer staring at a dashboard. We think half the future customer base is an AI agent acting on behalf of a marketer — so this actor is already exposed as a Model Context Protocol (MCP) tool through the official Apify MCP server. No SDK, no API-key juggling: point your MCP client at the URL below and your agent can ask "how visible is HubSpot vs Salesforce in ChatGPT and Perplexity on buyer-intent CRM queries?" and get the ground-truth validated dataset back as structured JSON.

Server URL (this actor only):

https://mcp.apify.com?tools=doesaiknow/ai-brand-visibility-tracker-chatgpt-perplexity-gemini

Authenticate with your Apify token (Authorization: Bearer <APIFY_TOKEN>) or the OAuth sign-in your client offers. Runs are billed to your Apify account at the same $0.30/query — agents pay exactly what humans pay, no separate plan, no monthly commitment.

Claude Desktop / claude.ai — Settings → Connectors → Add custom connector → paste the URL above.

Claude Code

$claude mcp add --transport http doesaiknow "https://mcp.apify.com?tools=doesaiknow/ai-brand-visibility-tracker-chatgpt-perplexity-gemini" --header "Authorization: Bearer $APIFY_TOKEN"

Cursor / VS Code / Windsurf (mcp.json)

{
  "mcpServers": {
    "doesaiknow": {
      "url": "https://mcp.apify.com?tools=doesaiknow/ai-brand-visibility-tracker-chatgpt-perplexity-gemini",
      "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
    }
  }
}

n8n / Zapier / Make / in-house agents — any MCP client that accepts a Streamable HTTP URL works with the same address.

How the agent flow works (a real scan takes 3–7 minutes):

1. The agent calls the actor tool (named doesaiknow--ai-brand-visibility-tracker…) with brand, queries (3–15) and optionally competitors, platforms, language, brandUrl. The call returns within waitSecs (max 45 s) with a runId and datasetId — the scan keeps running.
2. It polls get-actor-run with waitSecs: 45 until the status is SUCCEEDED (typically 4–10 polls).
3. It reads the results with get-dataset-items (clean: true): one item per scan with summary, competitors, per_platform_per_brand, per_query and top_cited_domains — the same output documented below.

Prompt to paste into Claude or Cursor:

Using the DoesAIKnow brand-visibility tool, scan HubSpot against Salesforce and Pipedrive on 5 buyer-intent CRM queries for the US market. Wait for the run to finish, then summarise AIS, mention rate and share of voice per engine, and list the queries where HubSpot is absent.

Tip for agents: keep tier at pro_auditor for real data. demo returns a free cached sample for a different brand and only shows the output shape.

---

🆚 How this AI Brand Visibility Tracker compares

vs. AI-visibility SaaS subscriptions (Otterly, AthenaHQ, Peec, Profound)

	Typical AI-visibility SaaS	This AI Brand Visibility Tracker
Entry price	€29–€489 / month (annual contracts common)	$0.30 per query, pay as you go
Setup	Account, onboarding call, contract	Zero setup — paste brand, click Run
AI engines covered	3–5 (depends on plan)	5 default + 2 optional (Grok, AI Mode)
Fan-out per query	None or 1–2 variants	~4 automatic variants
Ground-truth validation	Marketing copy says yes, reality varies	3-layer markdown gating, documented
Data format	Dashboards, rarely API	Structured JSON in your Apify dataset
MCP / AI agent integration	None	Live — one MCP tool call via mcp.apify.com
Kill switch	Cancel before renewal	No recurring bill to cancel

Bottom line: a 10-query audit here costs $1.80–$3.00. Otterly Lite starts at $29/month for 15 prompts ($1.93/prompt).

vs. building it yourself on raw LLM APIs

Roughly 40 engineering hours (scraping, proxy rotation, schema, validation) and 5+ API keys to manage, at $0.30–$0.50 per validated datapoint once tokens, proxies and orchestration are counted — against $0.011–$0.015 here with hallucination validation already built in.

vs. other Apify brand-visibility actors

Per-unit prices in this category are not comparable, because every actor bills a different unit. Competitors charge per one brand × one query × one engine. This actor charges per query, and one query is fanned out across every selected engine.

Same basket — 3 queries checked on 5 AI engines, priced from each actor's public pricing on 2026-09-16:

Actor	Billing unit	Cost of the basket	Real AI interactions you get
This actor (Gold+ tier)	query (fan-out ×4 × 5–7 engines)	$0.54	72
This actor (Free tier)	query (fan-out ×4 × 5–7 engines)	$0.90	72
santhej/ai-rank-tracker-pro	query × platform, + $0.25 report	$1.00	15
khadinakbar/ai-search-brand-monitor	brand × query × platform	$1.20	15
khadinakbar/llm-visibility-tracker	keyword × LLM	$1.35	15
khadinakbar/ai-search-visibility-tracker	keyword × query × platform	$1.35	15

That is 10–33% cheaper for the same scan, and 6.4× cheaper per actual AI interaction ($0.0125 vs $0.08–0.09). The headline "$0.30" looks higher only because it buys a whole query across every engine instead of a single check.

On top of that, this actor has volume tiers — $0.30 on Free, $0.18 on Gold and above. The alternatives above have none.

Beyond price, here is what the per-item number hides:

What you actually get per query	Cheapest Apify alternatives ($0.008–$0.10 per item)	This actor ($0.30/query)
AI engines covered	1–3 (often Perplexity only, or ChatGPT only)	5 (ChatGPT, Perplexity, Gemini, Copilot, Google AI Overview)
Real AI datapoints per unit you pay for	1	~20
Fan-out across related queries	No — one prompt, one answer	~4 variants per query, sourced from Google PAA + related
Ground-truth validation	No — LLM says brand X was mentioned, you trust it	Yes — literal markdown substring match, 3 layers
Hallucination inflation control	No — up to 5.6× inflated mention rates	Yes — validated numbers only
Real browser sessions vs. API	Often API-only (different answers than users see)	Real browser sessions
AI Visibility Score (AIS) with consistency gating	No	Yes — composite 0–100 score
Framing enum (leader / compared / …)	No	Yes — 7-class structured
Gap analysis	No	Yes — 5-class structured with severity
Entity resolution (dedup of "HubSpot", "HubSpot CRM")	No	Yes — 3-phase: normalize → prefix → LLM grouping
Per-platform × per-brand matrix	No	Yes — full matrix with platform-local SoV
Owned vs. earned citation split	No	Yes
Sentiment breakdown (positive / neutral / negative)	No or only positive	Full three-bucket
Top-cited domains ranking	No	Yes — with engine coverage + citation roles
Output format	Flat CSV or plain text	Structured JSON with typed enums
Cost per validated datapoint	$0.008–$0.10	$0.005–$0.020 (at Gold tier)

Per-item actors give you one scrape per unit billed. This actor gives you a full AI Brand Visibility audit — for less money in total, with data you can put in a board deck.

---

🔬 Why the numbers hold up

Ground-truth validation, 3 layers. Asked "which brands appear in this answer?", a downstream LLM routinely invents brands that were never there — in our benchmarks the worst offender inflated mention rate 5.6×. So mention rates come from a literal substring match against the raw response markdown, not from LLM extraction; sentiment, position and prominence are computed only for rows whose markdown actually contains the brand; and the consistency score runs on evidence rates, not LLM counts. Every response carries ground_truth_validated: true so you can tell the gate ran. No SaaS competitor advertises this.

Fan-out matched to buyer intent. Buyers don't ask "best CRM" once — they ask 3–5 variants. Each seed query expands into ~4 related queries sourced from Google People-Also-Ask, so a brand that misses the seed phrasing isn't scored as invisible.

Entity resolution. "HubSpot", "HubSpot CRM" and "Hubspot" are one brand, resolved in three phases (normalize → prefix → LLM grouping) before anything is counted.

Platform-local Share of Voice. SoV is computed per engine against tracked brands only — a global denominator counting every hallucinated brand makes the number look better and mean less.

🧑‍💼 Co-designed with a senior SEO / GEO analyst

The metric set, formulas, validation gates and output schema were co-designed with a senior SEO/GEO analyst who runs paid AI visibility audits for agency clients. Two consequences you can check: Share of Voice is tracked-only (global SoV — denominator counting every brand the AI ever hallucinated — was rejected as misleading), and the per-platform × per-brand matrix ships in the shape agencies already use, so the JSON drops into Looker or Sheets without re-shaping.

---

📊 What you get in the output

Section	What's inside
Summary	Your brand's AI Visibility Score (AIS), mention rate, share of voice, consistency score, sentiment breakdown, owned / earned citation split, top-10 aggregate strengths and weaknesses, dominant framing.
Competitors	Same aggregate metrics, one row per tracked competitor.
Per-platform	Each engine's coverage %, mention rate, AIS, average position, top-3 rate, sentiment breakdown. Sorted by AIS desc so [0] is your strongest engine.
Per-platform × per-brand matrix	One row per (engine × tracked brand). Answers "where am I winning, where am I losing" in one table.
Per-query	Every (query × engine) cell with framing, sentiment, position, gap class, opportunity type, markdown excerpt, strengths, weaknesses, and full citation list with domain types and roles.
Top cited domains	Ranked list of domains AI engines trust on your topic. Flags your own domain as is_brand_owned: true.
Cited Pages (owned domain)	Every URL of YOURS that AI engines cited: per-engine counts, avg position, and which pages to double down on. Included free with every paid scan. See the dedicated section below.
Brand Perception (opt-in, includePerception: true)	HOW AI describes each tracked brand: validated attributes, sentiment counts and recommended-vs-warned-against stance per engine. See the dedicated section below.
Upgrade CTA (demo and free tiers)	Counts of platforms, queries, domains, matrix rows hidden at this tier.

Full OpenAPI contract is in the source repo.

---

🎭 Brand Perception / Sentiment (opt-in add-on)

Visibility tells you whether AI mentions your brand. Perception tells you how: is ChatGPT calling you "affordable" or "unreliable"? Does Perplexity recommend you, warn against you, or merely list you? Set includePerception: true and that lands for your brand and every tracked competitor, computed from the answers the scan already collected — no extra engine round-trips.

"perception": {
  "attributes": [
    { "label": "affordable", "evidence_count": 12, "engines": ["chatgpt", "perplexity"],
      "sample_phrase": "one of the more affordable options in this category" }
  ],
  "per_engine": {
    "chatgpt":    { "stance": "recommended", "sentiment_counts": { "positive": 7, "neutral": 4, "negative": 0 } },
    "perplexity": { "stance": "mentioned",   "sentiment_counts": { "positive": 3, "neutral": 8, "negative": 1 } }
  },
  "overall_stance": "recommended",
  "overall_sentiment": "positive"
}

• attributes — tags merged from synonyms ("cheap", "low-cost" → "affordable"), each with evidence_count, source engines and a verbatim sample_phrase.
• stance per engine — recommended / warned_against / mentioned / absent.
• sentiment_counts per engine, plus the dominant values across all engines.

Grounded in the actual answer text, so nothing is invented. Billed as one perception event per run ($0.09–$0.15 by plan tier); never charged on demo, and not charged if the report can't be produced.

📄 Cited Pages — which of YOUR pages AI actually cites

top_cited_domains tells you which domains AI engines trust. Cited Pages goes one level deeper on the domain that matters most — yours. For every URL on your own domain that an engine actually cited, you get per-engine counts, average and best position, how many distinct queries surfaced it, and a double_down / maintain / low label.

"cited_pages": [
  { "url": "https://ahrefs.com/blog/seo-checklist/",
    "per_engine": { "chatgpt": 9, "perplexity": 4 },
    "avg_position": 2.3, "first_position_seen": 1,
    "distinct_queries": 6, "recommendation": "double_down" }
]

The same page cited by ChatGPT (which appends ?utm_source=chatgpt.com) and by Perplexity counts as one page — tracking parameters and www. variants are normalized before grouping.

No flag and no extra charge: it ships with every paid scan, re-aggregated from citations the scan already collects. Honest scope: these are pages observed in this scan — the actor doesn't crawl your site, so a page that wasn't cited on the scanned queries simply doesn't appear. Absence here is not evidence of a weak page.

🚀 Input — what you pass in

{
  "brand": "HubSpot",
  "category": "CRM software",
  "competitors": ["Salesforce", "Pipedrive", "Zoho CRM"],
  "language": "us",
  "queries": [
    "best CRM for marketing agencies",
    "HubSpot vs Salesforce for small business",
    "AI features in HubSpot CRM"
  ]
}

Every field is documented in the actor's Input tab. Four things that tab doesn't make obvious:

• queries are the cost driver — N × $0.30, min 3, max 15. Each expands to ~4 fan-out variants across your selected engines (~20 AI calls on the default 5). Write them in your customers' language.
• brandUrl matters only when another company shares your name: answers about the same-name different company stop counting as your visibility, and citations of your domain are attributed to you.
• platforms defaults to 5 engines (chatgpt, perplexity, gemini, copilot, ai_overview); grok and ai_mode are available and push a query to ~28 calls.
• includePerception adds one perception event per run ($0.09–$0.15 by plan) on top of per-query pricing.

📦 Sample output

Abridged — the full typed schema ships in the actor's Output tab and dataset_schema.json.

{
  "brand": "Ahrefs",
  "category": "SEO tools",
  "summary": {
    "ais": 74.6,
    "mention_rate": 89.6,
    "share_of_voice": 14.4,
    "consistency_score": 46.7,
    "avg_position": 2.0,
    "top3_rate_pct": 86.8,
    "sentiment_positive_pct": 39.7,
    "sentiment_negative_pct": 2.7,
    "dominant_framing": "leader",
    "owned_citation_pct": 9.3,
    "earned_citation_pct": 90.7,
    "aggregate_strengths": ["backlink analysis", "keyword research", "Site Explorer"],
    "aggregate_weaknesses": ["no free trial", "expensive", "steep learning curve"],
    "ground_truth_validated": true
  },
  "competitors": [
    { "brand": "Semrush", "ais": 67.2, "mention_rate": 82.0, "share_of_voice": 13.6,
      "aggregate_weaknesses": ["UI clutter", "weaker backlink data than Ahrefs"],
      "citation_mix": { "blog": 38.5, "media": 12.1, "review_site": 8.2, "brand_owned": 4.2 } }
  ],
  "per_platform_per_brand": [
    { "platform": "copilot",    "brand": "Ahrefs",  "ais": 84.7, "mention_rate": 98.0, "top3_rate_pct": 87.0 },
    { "platform": "perplexity", "brand": "Ahrefs",  "ais": 73.6, "mention_rate": 90.0, "top3_rate_pct": 93.0 },
    { "platform": "copilot",    "brand": "Semrush", "ais": 62.4, "mention_rate": 78.0, "top3_rate_pct": 82.1 }
  ]
}

What that already tells you without further analysis: Ahrefs owns Copilot (AIS 84.7, 98% mention rate) and converts to top-3 on Perplexity in 93% of answers, while 90.7% of its citations are earned rather than owned — the brand is being recommended by third parties, not just citing itself. The gap to close is consistency at 46.7: the brand appears often, but not dependably across phrasings.

🧭 Who this AI Brand Visibility Tracker is for

• SEO & GEO agencies running monthly AI Brand Visibility audits for clients. Use this to export directly into Looker or a client dashboard.
• B2B SaaS brand managers who need to prove "we won the AI mention race" in a quarterly board deck. Full competitor comparison included.
• LLM SEO consultants focused on AEO (Answer Engine Optimization) and GEO (Generative Engine Optimization) — the per-query gap class and opportunity type are the work order for your editorial calendar.
• Competitive intelligence & RevOps teams tracking competitor share-of-voice across ChatGPT, Perplexity, Gemini and Copilot — without paying $1,600/mo for a generic CI platform.
• Content strategists looking to see exactly which query intents leave them absent from AI answers.
• Sales Ops personalising cold outreach at scale: 1 query per prospect via Clay or Apify API.
• Freelance SEO consultants who don't want a $99+/month subscription just to run one audit.
• AI agents (Claude Desktop, Cursor, ChatGPT custom GPTs) querying the dataset natively via MCP.

---

⏱️ How long does a scan take?

Queries	Approx. runtime	Approx. AI checks
3 (default)	3–5 min	60–84
10	8–15 min	200–280
15 (max)	15–25 min	300–420

Lower bound = 5 default engines, upper = all 7. One query ≈ 4 variants × engines selected.

A single scan accepts up to 15 queries — sized so even a max scan finishes inside the 30-minute run budget. Need more coverage? Split it across multiple runs. Scans are parallel across engines; the bottleneck is slower AI engines (ChatGPT, AI Mode) on heavy load. If one engine lags, the scan finalizes once ~90% of responses are in — the result carries a partial flag plus tasks_completed / tasks_total, so you always know the coverage and one straggler never costs you the whole run. Your Apify dataset populates the moment aggregation finishes. PPE events fire on completion: a near-complete result (a handful of stragglers missing) still bills, but a substantially incomplete result — or a run that errors out / hits the platform timeout before the result is ready — is not charged.

⏱️ Calling via the Apify API? Set your run's timeout to at least 1800 seconds. A timeout passed in an API run request overrides the actor's default, so a low hardcoded value (e.g. 600) can abort a scan before it finishes — even when the backend would have completed it. The actor's own UI default is already 1800s; this note is only for API / SDK callers.

---

🛡️ Legal & compliance

This actor only queries publicly available AI search interfaces (consumer ChatGPT, Perplexity, Gemini, Microsoft Copilot, Google AI Overview / AI Mode). It does not bypass authentication, scrape gated APIs, or store user-generated content. Brand and category strings you submit are processed transiently for the scan; results are written into your Apify dataset under your account. We don't share or sell scan content. Each AI engine is queried per its public Terms of Service through real-browser automation; if an engine returns a rate-limit or compliance signal, the scan retries within published limits and the failure is surfaced in the result. GDPR / CCPA compliance applies to the brand/category strings you submit — don't pass personally identifying information.

---

🧰 FAQ

What exactly counts as 1 query? One topic or question you care about. Behind the scenes we expand it to 3–5 semantic variants (from Google PAA + related) and run each across 5 engines. You pay once; you get ~20 real AI data points.

Do I need to bring my own OpenAI / Anthropic / Google API keys? No. Everything is included in the $0.30 per query.

What happens if a scan fails mid-way? Every task is idempotent (tracked by a unique correlation key). If one AI engine throws, we retry automatically. The PPE event fires only on successful completion, so a dead-ended scan isn't charged.

Can I trust the numbers? Yes, and the system is designed around that question. Every metric except Sentiment is backed by a literal markdown substring match. Sentiment is LLM-classified but gated by markdown evidence. Every response carries ground_truth_validated: true confirming the validation ran.

Is my input private? Brand and category are public information. Results live in your Apify dataset under your account. We don't share or sell scan content.

Can I use this AI Brand Visibility Tracker for a client's brand? Yes. The output is a complete, self-contained AI Brand Visibility report you can deliver as-is to clients.

Can I call this from Claude, Cursor or my own AI agent (MCP)? Yes, today. The actor is exposed as an MCP tool through the Apify MCP server — see the MCP section above for the server URL and client configs (Claude Desktop, Claude Code, Cursor, VS Code, n8n / Zapier / Make). Your agent starts the scan, waits for the run, then reads the dataset; billing is the same $0.30/query on your Apify account, no monthly commitment. A native hosted MCP endpoint with higher-level tools is on the roadmap.

Refund policy? Apify's standard PPE model: you're only billed on successful task completion. Failed or partial scans are not charged.

---

🗺️ Roadmap

No ETAs; everything lands behind the per_* fields you already consume, so changes stay backward compatible.

Next: a native MCP endpoint with higher-level tools — compare brands, track a query set over time, explain a gap — one call, no polling · executive summary (2–4 sentence plain-English read of your profile).

Planned: discovered brands outside your competitors[] list · content opportunity map from the fan-out pass · Clay / Zapier / Make nodes · Looker / Sheets export templates.

Shipped recently: Cited Pages per owned domain · Brand Perception / Sentiment (opt-in) · brandUrl disambiguation.

🧾 Changelog

2026-09-16 — v0.8.2: MCP — callable from Claude, Cursor and AI agents today

• New (docs): the actor is exposed as an MCP tool through the Apify MCP server; the README now has the server URL, client configs (Claude Desktop, Claude Code, Cursor / VS Code) and the run → poll → dataset flow for agents.
• Improved: queries and tier input descriptions rewritten so AI agents pick real buyer questions and the paid tier instead of the free demo sample.
• No change to input or output shapes, no billing change.

2026-09-16 — v0.8.1: reliability fix + honest failures

• Fixed: between 2026-08-11 and 2026-09-16 runs could fail immediately after start with a connection error due to a deployment configuration issue on our side. The fix is live; no run that failed this way was charged (billing happens only after a result is delivered). We're sorry for the trouble.
• Improved: the scan submission now retries transient network errors, and a failed run is reported as FAILED with a clear status message instead of finishing as succeeded with no data.
• Fixed: selecting the demo tier returned a validation error; the free cached preview works again.
• No change to input or output shapes, no billing change.

2026-08-06 — v0.8: brandUrl — disambiguation for shared brand names (free, opt-in)

• New: brandUrl input (optional). Give the scan your website (mercury.com) and brands that merely share your name stop polluting your results: an answer about a same-name different company no longer counts as your visibility, citations of your domain (and subdomains) are attributed to you as brand-owned sources, and a reference to your domain counts as a mention even when the name is spelled differently. Requested by a user via the actor's Issues tab — thank you!
• No new billable event, no price change — the domain rides along in the same scan and the same LLM calls.
• No change to existing scans: leave the field empty and matching stays name-only, byte-for-byte as before.

Older entries live in the actor's Issues tab.

🔗 Sibling actors from the same doesaiknow developer

• Keyword Metrics Pro — bulk Google + Bing search volume + CPC + trend data ($1.35 per 1,000 keywords).
• AI Keyword Clustering Tool — AI-driven topical clustering with bulk SERP MERGE/SPLIT logic, built for AEO/GEO content strategy.
• Competitor Keyword Research — see any site's ranked keywords to map a competitor's keyword footprint.

---

🤝 Built by

doesaiknow.com — the only AI Brand Visibility Tracker built around 3-layer Ground-Truth Validation to eliminate LLM hallucination from your data, co-designed with a senior SEO / GEO analyst, and built to ship the same dataset to Apify, MCP-aware AI agents, BI tools and APIs under a single pay-per-query economic model.