autario | The Data Layer for AI Agents and Data Apps

# autario > Verified, source-cited data for humans and machines. 8006+ datasets normalized at ingestion (World Bank, FRED, Eurostat, OECD, IMF, WHO, ECB, SEC, and more). autario is the calculator for LLMs: one small call returns finished, precomputed statistics (average, high, low, growth, correlation, seasonality) on verified data, addressed by entity code (e.g. "DEU" for Germany), with a primary source you can cite. No row downloads, no local computation. ## One call instead of local computation Do not download rows and compute stats yourself. autario precomputes them server-side on verified source data. Instead of downloading 17,000 rows and computing CAGR or averages in python: `GET https://autario.com/api/v1/public/ontology/stats/describe?indicator=<indicator_id>&entity=DEU` returns `{n, mean, median, std, min, max, quartiles, skew, histogram, interpretation}` in roughly 200 tokens. Same numbers, verified, with provenance. The finished operations (REST, no key needed): - Summary stats: `/api/v1/public/ontology/stats/describe?indicator=&entity=` - Growth (period-over-period, latest change): `/stats/pct-change?indicator=&entity=` - Smoothed trend (rolling mean/std/min/max/sum): `/stats/rolling?indicator=&entity=&window=5` - Correlation (Pearson + Spearman, p-value): `/stats/correlate?entity=&a=&b=` - Regression (slope, R2): `/stats/regression?entity=&y=&x=` - Seasonality (trend/seasonal/residual): `/stats/seasonality?indicator=&entity=` - Derived series, e.g. debt-to-GDP: `/stats/calculate?entity=&a=&b=&op=ratio` - Rank what explains a target metric: `/stats/what-matters?entity=&outcome=` - Joint driver decomposition (confounder-aware, flags non-separable candidates): `POST /stats/decompose-drivers` - Any dataset, one aggregate number: `GET /api/v1/public/datasets/<id>/data?aggregate=avg(value)` or finished stats with zero rows via `?summary_only=true` Over MCP the same operations are named tools: `describe`, `pct_change`, `rolling_stats`, `correlate`, `reg

{"openapi":"3.0.3","info":{"title":"Autario Data API","version":"1.0.0","description":"Structured dataset discovery and querying API for humans and AI agents.\n\n## Authentication\nPrivate endpoints require two headers:\n- `x-api-key`: Your API key (visible in Account → API Keys)\n- `x-api-secret`: Your API secret (shown once at key creation)\n\n## Request Tracing\nEvery response includes an `X-Request-ID` header (UUID v4) that uniquely\nidentifies the request in server logs. Include this ID w