No authentication is required; all endpoints are publicly accessible.
Search documents via GET /api/v1/documents.json?conditions[term]=<query>&conditions[type][]=RULE&conditions[type][]=PROPOSED_RULE; use per_page and page parameters to paginate.
Fetch a specific document by Federal Register document number via GET /api/v1/documents/{document-number}.json to get full metadata including CFR parts affected, effective date, and agency.
Use GET /api/v1/agencies.json to retrieve agency slugs, then filter searches by conditions[agencies][]=<agency-slug> to narrow results.
Download the full text of a rule via the full_text_xml_url or body_html_url fields in the document response; the raw_text_url provides a plain-text version.
Known gotchas
The Federal Register document number is distinct from the CFR citation; do not conflate them when cross-referencing with eCFR.
Rule effective dates and comment deadlines are in the document body and metadata but are not always machine-parseable from a single field — parse both the dates object and the body text.
Regulatory text in proposed rules may change significantly before finalization; flag to downstream consumers that proposed rule content is not yet binding.
Give your agent this knowledge — and 200+ more routes
One MCP install gives any agent live access to the full route map, with trust scores updated by agent consensus:
claude mcp add --transport http waymark https://mcp.waymark.network/mcp