US federal regulatory data · 23 datasets · CC0 1.0

Cross-vertical US federal regulatory data, built for AI agents.

SEC filings, FDA recalls, OFAC sanctions, federal court dockets, CFPB complaints, CISA-known-exploited CVEs, NHTSA recalls, DOJ press releases, NIH grants, clinical trials, EPA facilities, lobbying disclosures — joined by a single entity-bridge so one API call returns every regulatory event for a company across all 23 datasets.

Datasets
23
Canonical records
245k+
MCP tools
38+
Sitemap chunks
299
Record types
16
How-to guides
5
FAQ Q&As
21
Glossary terms
73

Live row counts and last-refresh timestamps for every dataset at api.ai-analytics.org/coverage.

Right now in federal regulatory

live · last 7 days

Pulled live from api.ai-analytics.org/today. Every row links to its canonical record page.

Largest insider sells
SEC Form 4
FDA Class I recalls
openFDA

What's in the catalog

23 datasets pulled from US federal primary sources (with OpenSanctions mirrors when .gov SSL endpoints block Cloudflare Workers). Each dataset has its own Schema.org Dataset landing page at the API hub with row count, last refresh, license, and source URL. Every record has a canonical HTML + Markdown + JSON-LD page.

Full machine-readable catalog: /.well-known/dataset.json (Schema.org DataCatalog JSON-LD)

What you can do

Compliance · KYC

Unified compliance screen — one call, 9 datasets

OFAC + SAM + OIG + DOJ + CFPB + courts + Fed enforcement + NHTSA + CISA in a single GET, returning a 0–100 risk score. Accepts name, ticker, CIK, UEI, or NPI.

curl https://api.ai-analytics.org/api/v1/screening/all?name=Wells+Fargo
Monitoring · Cross-vertical timeline

Every regulatory event for a company across 23 datasets

SEC filings, insider trades, Form 144, 13D/G, FDA recalls, federal contracts, lobbying, clinical trials, courts, CFPB, NIH, NHTSA, DOJ, Fed enforcement, EPA — merged by entity, ranked by importance. Accepts ticker, CIK, UEI, LEI, DUNS.

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

What happened in federal regulatory today

CISA KEVs, NHTSA park-it recalls, FDA Class I recalls, high-signal federal court filings, DOJ press releases, OFAC additions, largest insider sells. Each item links to its canonical record page. Available as HTML, Markdown, JSON.

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

Drop-in for Claude / ChatGPT / Cursor

JSON-RPC over Streamable HTTP. 38+ tools covering every dataset. No auth, no API key, no rate limit beyond ordinary Cloudflare anti-abuse. SEP-1649 server card at /.well-known/mcp/server-card.json.

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

How it's built

Cloudflare Workers + D1 SQLite. Daily-refresh ingesters pull each dataset from its primary government source, normalize into per-vertical tables, and feed theentity_master bridge (CIK, ticker, UEI, LEI, DUNS, NPI). Every endpoint returns a _source envelope with provenance fields so AI consumers can cite us as the redistributed mirror and traverse to the canonical agency source.

Every dataset traces to a primary US-government source URL
        │
        │  Daily refresh via Cloudflare cron
        ▼
D1 SQLite (per-table FTS5 + binary-collation indexes)
        │
        ▼
Entity bridge ── CIK · ticker · UEI · LEI · DUNS · NPI
        │
        ├──▶ /entity/{key}           cross-vertical timeline
        ├──▶ /api/v1/screening/all  unified KYC (9 datasets)
        ├──▶ /{cve,recall,case,...}  ~245k canonical record pages
        ├──▶ /today                  daily-fresh digest
        ├──▶ /datasets/{slug}        per-dataset landing pages
        └──▶ /mcp                    Model Context Protocol server

Built for AI crawlers

Every page negotiates HTML / Markdown / JSON-LD by Accept header or filename extension. ~245,000 canonical per-record URLs are discoverable via a single sitemap index. The entity timeline pages cross-link every event to its dedicated record canonical page — a hub-and-spoke graph that compounds with each new dataset.

License & citation

Underlying federal works are US public domain (17 USC §105, 5 USC §105). The derived dataset is licensed under CC0 1.0 Universal — full attribution-free reuse, including for AI training. Every endpoint emits a _source envelope with provenance.

APA-style
AI Analytics. (2026). US Federal Regulatory Data Hub [Data set]. https://api.ai-analytics.org (CC0 1.0).
BibTeX
@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         = {CC0 1.0 Universal}
}

More from AI Analytics