Market data your AI agent can buy on its own.

Twenty-three years of US equity prices, SEC fundamentals, and filings. Your agent asks, pays a fraction of a cent, and moves on — no keys, no accounts, no humans in the loop.

Read the docs Connect an agent
23 yrs
of history, 2003 to today
16,000+
tickers on active days
8 timeframes
3-minute bars up to 4-hour bars
$0.001
starting price per query
How it works

One request. One payment. Done.

Traditional data vendors were built for humans — contracts, sales calls, monthly minimums. Cabrini is built for software that buys what it needs, when it needs it, using the x402 payment standard.

1

Ask for data

Your agent requests any ticker and date — Apple on the day the iPhone launched, or every symbol that traded last Tuesday.

2

Pay in passing

The response quotes an exact price. The agent signs a USDC micropayment on Base and retries — no account, no invoice, no human.

3

Get the answer

A full session of bars comes back at whatever timeframe the agent asked for — open, high, low and close, the same values as percentage move from the daily open, plus volume and trade count.

# Ask POST /v1/query {"ticker": "AAPL", "date": "2024-01-02"} # Server quotes the price 402 Payment Required · $0.025 USDC on Base # Agent signs, retries with proof POST /v1/query + X-PAYMENT # Data arrives 200 OK · 130 three-minute bars for AAPL
Pricing

Pay for the question, not the platform.

Every price is quoted up front in the response itself. No tiers, no seats, no minimum spend — a research run that costs a dollar today costs nothing tomorrow if you don't run it.

POST /v1/query
$0.025
One ticker, one full trading day, at the timeframe you choose.
GET /v1/tickers
$0.005
Every symbol that traded on a given date — 7,000 to 16,000+.
POST /v1/range
$0.01 / day
One ticker across multiple days — no day limit.
POST /v1/batch
$0.02 / ticker
Multiple tickers for a single date in one request — no ticker limit.
POST /v1/daily
$0.001 / year
Daily bars — two decades of history for two cents. Split-adjusted on request.
POST /v1/scan
$0.10
Screen every US stock on a date — gaps, moves, volume. One query instead of thousands.
POST /v1/bars
$0.015 / day
Multi-day intraday bars at any timeframe — no day limit.
POST /v1/fundamentals · /v1/insiders
$0.02
Quarterly financials and insider trades, normalized from SEC EDGAR.
POST /v1/filings
$0.01 – $0.05
SEC filing index. Add section extraction (risk factors, MD&A) for $0.05 — saves parsing 300-page documents.
POST /v1/brief
$0.25
The flagship: price action, fundamentals, insiders, and splits — joined in one call. Replaces ~20 queries.
The data

Deep enough for real research.

This isn't a sample set. It's every US trading session since September 2003 — cleaned, normalized, and refreshed daily.

Every US equity

Large caps, small caps, ETFs, and the long tail — everything that printed a trade, including symbols that have since delisted.

Full intraday detail

Every bar carries absolute open, high, low and close, the same four values as percentage move from the daily open, plus volume and transaction count and a nanosecond-epoch timestamp. Daily bars add VWAP and volatility.

SEC EDGAR fundamentals

Quarterly financials (revenue, net income, EPS, margins), insider trades from Form 4, and full filing index with optional section extraction — risk factors, MD&A, and more.

Two decades of context

The 2008 crisis, the flash crash, the meme-stock era — 23 years of market behavior to train on and test against.

Wiring up an agent?

Cabrini speaks the protocols agents already understand — connect over MCP, discover via A2A or llms.txt, pay with x402. Everything technical lives in one place.

MCPA2Ax402OpenAPIllms.txt
Agent integration guide