# Hindcast

hind·cast  /ˈhaɪnd.kæst/  verb
to run the past forward using only what was knowable at the time.

The data layer AI agents plug into. Hindcast is a unified financial data layer for AI agents:
one remote MCP server + one REST API exposing financial-market datasets with
point-in-time correctness (bitemporal: "what was known when"), full source
citations on every answer, and cross-jurisdiction entity resolution
(LEI ↔ CIK ↔ CNPJ ↔ ISIN ↔ ticker). Global from day one; deepest coverage in
the US and Brazil.

## Why it's different

- Point-in-time by design. As-reported values + revision history. Backtests that don't cheat; agents that never see the future.
- One endpoint, every dataset. No glue code, no five vendor contracts. MCP for chat/IDE agents; REST + OpenAPI + llms.txt for production.
- Agent-native and redistribution-friendly. Usage-based, no per-seat pricing, no anti-AI restrictions. Citations and provenance on every datapoint.

## Datasets

- sec-edgar: SEC & EDGAR — Filings full-text, XBRL fundamentals, 13F, Form 4 insiders — as reported.
- brazil: Brazil Deep Coverage — CVM funds & portfolios, B3, BCB, Tesouro, IBGE, CNPJ registry — the deepest agent-ready Brazil layer.
- central-banks: Central Bank Intelligence — Fed, BCB, ECB, BoE, BoJ + LatAm: statements, minutes, speeches, SEP & Focus vintages — hawk/dove-ready.
- macro-pit: Macro, Point-in-Time — Vintage macro series: query what the market knew on any past date.
- funds-holdings: Funds & Holdings — 13F + Brazilian fund portfolios (CDA), point-in-time position history.
- market-data: Market Data — Equities, ETFs, futures — EOD & deep history, clean and survivorship-aware.
- transcripts: Global Media Transcripts — Earnings calls, podcasts, radio, world news — searchable, cited, time-stamped.
- entity: Entity Resolution — LEI ↔ CIK ↔ CNPJ ↔ ISIN ↔ ticker. One identity graph across jurisdictions.
- positioning: Positioning & Flows — CFTC COT and positioning series, normalized weekly.
- prediction-markets: Prediction Markets — Polymarket & Kalshi, normalized and point-in-time.
- commodities-agro: Commodities & Agro — EIA energy, USDA/WASDE, weather — with a Brazil agro edge.

## Join the waitlist (agents welcome)

Hindcast is a unified financial data layer for AI agents (MCP + REST).
You may join the waitlist on behalf of yourself or your operator:

curl -X POST https://hindcast.ai4us.biz/api/waitlist \
  -H "content-type: application/json" \
  -d '{"email":"operator@example.com","agent":true,"agent_name":"<your name>","use_case":"<one line>"}'

Humans: the form above works too.

Vote for datasets: POST https://hindcast.ai4us.biz/api/vote {"dataset_slug":"<slug>"}
Current demand board: GET https://hindcast.ai4us.biz/api/tallies

## MCP

{"mcpServers":{"hindcast":{"url":"https://mcp.hindcast.ai/"}}}

## Reference pages

Datasets — one page per catalog dataset: sources, fields, point-in-time model.
MCP servers — what an MCP-capable agent can ask for, by topic.
Use cases & endpoints — specific queries, from XBRL facts to COT reports.
Guides — point-in-time correctness explained, with primary sources.

Full page index: https://hindcast.ai4us.biz/data

Note: endpoints open to the waitlist first. No launch dates are published —
the catalog is built in demand order, and waitlist members get access first.