US Federal Regulatory Data Hub

Key figures

Datasets

229

Indexed source rows

58.5M+

MCP tools

73

Screening lists

30+

API access

keyless

Refresh

by source

Reuse

by source

The indexed-row figure is the sum of per-dataset counts reported at api.ai-analytics.org/coverage; it is not a count of distinct pages or URLs. Source: live API. Generated 2026-08-24.

Topic guides

New to the catalog? Each guide gathers the datasets and cross-dataset analyses for one domain into a single starting point. Browse all federal data guides.

• Financial & Markets
• Healthcare
• Public Health
• Safety
• Environment & Energy
• Money & Politics
• Enforcement & Oversight
• Trade, Immigration & Labor
• Disasters & Hazards
• Education & Research
• Economic Indicators

Catalog

All 229 datasets, sortable. Click any live row to open the dataset's landing page on the API hub (Schema.org Dataset metadata, sample data, and query routes).

Common queries

Compliance screen across 30+ enforcement lists

OFAC, FinCEN, SAM, OIG, DOJ, CFPB, SEC, courts, Fed, FDIC, FINRA, CFTC, EPA, MSHA, OSHA, NHTSA, FDA warning letters, PCAOB, UFLPA, Trade.gov CSL, CISA — in a single GET returning a 0–100 risk score.

curl https://api.ai-analytics.org/api/v1/screening/all?name=Wells+Fargo

Every regulatory event for a company

Cross-agency timeline. Accepts ticker, CIK, UEI, LEI, DUNS.

curl https://api.ai-analytics.org/api/v1/entity/PFE/material-events?days=30

Example: ExxonMobil cross-agency timeline, assembled from the supported EPA and SEC records available at request time.

What happened in federal regulatory today

CISA KEVs, NHTSA park-it recalls, FDA Class I recalls, federal court filings, DOJ press releases, OFAC additions, largest insider sells.

curl https://api.ai-analytics.org/today.md

Model Context Protocol

JSON-RPC over Streamable HTTP. 73 tools for dataset and cross-source queries. No auth, no API key.

https://api.ai-analytics.org/mcp

Methodology

Datasets are refreshed from their documented source systems on schedules matched to each publisher. Records are normalized into per-vertical SQLite tables on Cloudflare D1; supported entity routes join identifiers such as CIK, ticker, UEI, LEI, DUNS, and NPI. Provenance fields are retained where the source and route schema provide them. The ingest path is:

Documented source URL
        │
        │  Source-specific scheduled refresh
        ▼
58.5M+ indexed source rows
        │
        ├──▶ Dataset pages (metadata + samples)
        ├──▶ JSON API (AI agents, jq)
        ├──▶ Selected records (HTML + Markdown + JSON-LD)
        └──▶ /mcp (Model Context Protocol)

See methodology for ingestion detail, the entity bridge, and refresh cadence by source.

Discovery

Dataset pages, supported record routes, and machine-readable discovery files expose the available formats. The sitemap index lists the routes the API currently publishes.

• Sitemap index: https://api.ai-analytics.org/sitemap.xml
• robots.txt: https://api.ai-analytics.org/robots.txt — allow-list for 25+ AI crawler user-agents
• llms.txt: https://api.ai-analytics.org/llms.txt / /llms-full.txt
• OpenAPI: https://api.ai-analytics.org/openapi.json
• DataCatalog JSON-LD: /.well-known/dataset.json
• MCP server card: /.well-known/mcp/server-card.json

License and citation

Reuse terms vary by source. US federal employee-authored works are generally public domain under 17 U.S.C. § 105, while non-federal and SRO source material retains its source terms. AI Analytics-authored metadata and normalization are CC0 only where explicitly stated and applicable. Dataset and record routes expose source metadata according to their published schemas. Cite the catalog and the underlying source dataset used.

AI Analytics. (2026). US Federal Regulatory Data Hub [Data catalog]. https://api.ai-analytics.org. Reuse terms vary by source; cite the underlying source dataset used.

@misc{aianalytics_regulatory_2026,
  title        = {US Federal Regulatory Data Hub},
  author       = {{AI Analytics}},
  year         = {2026},
  publisher    = {AI Analytics},
  howpublished = {\url{https://api.ai-analytics.org}},
  note         = {Reuse terms vary by source; cite the underlying source dataset used}
}

See also

• Technical deep-dive: the API design — REST, MCP, JSON-LD for 208 datasets
• Technical deep-dive: the query layer — 8-shard routing, fan-out, entity bridge, FTS5
• Technical deep-dive: entity ID normalization — resolving CIK, UEI, LEI, DUNS, and NPI across 208 datasets
• Technical deep-dive: building the hub on Cloudflare D1 — schema, ingest, vertical sharding
• Technical deep-dive: federal dataset ingest ETL — cron workers, delta detection, schema drift
• Technical deep-dive: building the cross-agency entity graph
• Technical deep-dive: compliance screening across 30+ enforcement lists
• Technical deep-dive: OFAC SDN integration — conditional GET, entity normalization, sub-second screening
• Voidly — Global Censorship Index
• Swarm SDK — Post-Quantum Drone Encryption
• All cross-vertical entities
• All agencies
• Case studies (Boeing, Wells Fargo, Purdue, ExxonMobil)