The Agent Storefront
Ask your AI assistant if AI can find you. Then fix it — without leaving the chat.
When someone asks ChatGPT, Claude, Gemini, or Perplexity about your industry, do they find you? FlowBlinq's Agent Storefront answers that question inside the assistant you already use. Run a free visibility scan, then buy the full audit — all in one conversation.
17,800+ AI queries analyzed · 4,700+ pages audited · Tested across ChatGPT, Claude, Gemini, and Perplexity
What this is
FlowBlinq Agents is an MCP server that lets any AI assistant run an AI-visibility scan on a website and buy the full audit in the same conversation. It connects to Claude, ChatGPT, or any Model Context Protocol client. The free scan checks whether 14 AI crawlers can read and cite a site; the $10 audit crawls 250 pages and returns the real citation behavior plus a prioritized fix list. FlowBlinq is the first AI-visibility (GEO) company you can buy through an AI agent.
Setup
Add to Claude in 60 seconds.
No signup. No credit card. No API key. The scan is free and authless.
- 1Open Claude → Settings → Connectors → Add custom connector.
- 2Paste the server URL:
https://agents.flowblinq.com/api/mcp - 3Leave authentication set to None and save.
- 4Ask Claude: “Check the AI visibility of [yourdomain.com].”
Claude runs the scan and hands back a score out of 100, a per-crawler access table, and your top three gaps. Want the full picture? Ask Claude to “get the full audit” and it returns a checkout link for the $10 report.
Using ChatGPT or another MCP client instead? Point any Streamable-HTTP MCP client at the same /api/mcp URL. To poke at it directly, run npx @modelcontextprotocol/inspector, choose Streamable HTTP, and paste the URL.
What you can do
Six tools. One connection.
The scan is free and needs nothing. The audit is a one-time $10. Citation tools bill against a FlowBlinq credit balance, or an autonomous agent can pay per call over x402.
Credits: 1 credit = $0.10.
Free — no account
| Tool | What it does | Price |
|---|---|---|
check_ai_visibility | Instant teaser scan. Per-crawler access across 14 AI crawlers, an llms.txt check, schema/JSON-LD check, a JS-wall check (does an agent see an empty page?), a 0–100 score, and your top 3 gaps in plain English. | Free |
One-time
| Tool | What it does | Price |
|---|---|---|
get_full_audit_checkout | Returns a Stripe checkout link for the full audit: a 250-page crawl, real citation behavior across the major AI engines, and a prioritized fix list. | $10 |
get_audit_status | Checks the progress of a purchased audit. | Free |
Credit-billed (bring a FlowBlinq API token)
| Tool | What it does | Price |
|---|---|---|
run_citation_check | Asks one AI engine one buying-intent question and reports whether you're cited and where. | 2 credits ($0.20)per engine-prompt · Claude engine 4 credits ($0.40) |
run_citation_map | Runs the same question across all four AI engines — OpenAI, Anthropic, Perplexity, Google — and maps who gets cited. | 10 credits ($1.00)4 engines |
run_share_of_voice | Four-engine share-of-voice against up to five competitors: your SoV %, and who ranks above you. | 10 credits ($1.00)4 engines + up to 5 competitors |
The 14 AI crawlers we check: GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User, anthropic-ai, PerplexityBot, Perplexity-User, Google-Extended, GoogleOther, Bingbot, CCBot, Amazonbot, meta-externalagent.
Others report. We fix.
The audit doesn't stop at a PDF of problems — it tells you exactly what to change so AI engines start citing you.
For developers & autonomous agents
Every citation tool is payable by an agent over x402.
Every citation tool is payable by an autonomous agent over x402 — the HTTP-native payment standard — in USDC on Base. No human, no login, no checkout page. Your agent calls the endpoint, receives a 402 Payment Required, settles the exact price on-chain, and gets the result in the same request.
- Single citation check — 1 question × 1 engine$0.20 USDC (Claude engine $0.40)
- Citation map — 1 question × 4 engines$1.00 USDC
- Share-of-voice — 4 engines + up to 5 competitors$1.00 USDC
This is, as far as we know, the first AI-visibility audit an autonomous agent can buy without a human in the loop. Endpoints are discoverable through the CDP x402 Bazaar. Prices are fixed, settlement is on Base, and there's no subscription — an agent pays only for the calls it makes.
Building on this? Full docs live at agents.flowblinq.com.
FAQ
Common questions.
What does the free scan actually check?+
Whether 14 AI crawlers (GPTBot, ClaudeBot, PerplexityBot, and more) are allowed to read your site, whether you have an llms.txt file, whether your pages carry schema markup, and whether your content is trapped behind a JavaScript wall that agents can't see. It returns a 0–100 score and your top three gaps. It takes seconds and needs no signup.
How is the $10 audit different from the free scan?+
The free scan reads your site's front door — access, schema, and structure. The $10 audit crawls up to 250 pages and measures what the AI engines actually say about you: whether they cite you, where you rank, and a prioritized list of what to fix. The scan tells you if the door is open; the audit tells you what's inside.
Do I need an account or a credit card to try it?+
No. The scan is authless and free — add the connector to Claude and ask. You only pay when you buy the $10 audit (Stripe) or run a credit-billed citation tool (a FlowBlinq API token).
Which AI assistants does this work with?+
Any Model Context Protocol client. That includes Claude via custom connectors today, and any MCP-compatible assistant pointed at https://agents.flowblinq.com/api/mcp. Autonomous agents can transact directly over x402.
Is my data safe? What do you store?+
The free scan is stateless — we fetch your public pages the same way an AI crawler does and don't require any login. Paid audits run through Stripe; we never see your card. Full details are in our privacy policy at flowblinq.com/privacy.
Find out what AI says about you — from inside your AI assistant.
The scan is free and takes about a minute to set up.