vaaya / discover / structured scrape

Structured scrape for AI agents

Extract typed fields from pages — prices, specs, contacts — to a schema you name, instead of raw HTML.

from 1¢

What it's for

Extract specific, typed fields from a page instead of raw text.

Name the schema — price, specs, contact info, whatever you need.

Point it at one URL or several and get back the same shape each time.

Good for comparing pricing pages, spec sheets, or contact listings.

How to ask your agent

Connect Vaaya, then just say it in plain language. For example:

❯Extract name, price and features from these 5 pricing pages.

❯Pull the spec table from these product pages as JSON.

What you get back

{
  "data": [
    { "name": "Starter", "price": "$29/mo", "features": ["5 seats", "Email support"] },
    { "name": "Growth", "price": "$99/mo", "features": ["25 seats", "Priority support"] }
  ]
}

Pricing

from ~1¢ per page extracted. Billed per call in cents, capped by your max, every call on the ledger. Failed calls are not billed.

Give your agents this.

Connect Vaaya once, then describe the outcome. It picks the right capability, runs it, and pays per call.

npx @vaaya/mcp install