MCP server for Regulations.gov: search federal dockets and fetch rulemaking documents
Four tools with clear verb-noun naming (ping, search_dockets, get_docket, list_documents). All have substantive descriptions (100-200 chars, well within baseline). Input schemas are complete with types and descriptions. Tool annotations present and correct (read_only_hint, idempotent_hint, open_world_hint). Output schemas documented via docstrings. Pagination parameters properly constrained (page 1-20, page_size 5-250). Error handling includes validation and recovery guidance (e.g., 'get IDs from search_dockets rather than guessing them'). Main gaps: no enum constraints on agency_id or document_type filtering; output field documentation is implicit in docstrings rather than explicit schema definitions; no per-parameter type hints in descriptions (e.g., 'page must be integer 1-20' stated in description but not enforced at schema level).
Fetch one docket's full detail from Regulations.gov by its exact ID. Returns id, title, agency_id, docket_type, abstract (the docket's own summary of what the rulemaking does), keywords, rin (Regulation Identifier Number), and last_modified. Raises a not-found error for an ID that does not exist; get IDs from search_dockets rather than guessing them.
List the documents filed in one Regulations.gov docket. Returns document summaries: id, title, document_type (Proposed Rule, Rule, Notice, Supporting & Related Material, ...), posted_date, fr_doc_num (Federal Register document number), open_for_comment, comment_end_date, and withdrawn. A docket ID that matches nothing yields an empty list, not an error.
Report server health and configuration status without calling the API. Use this first if other tools fail: it tells you whether an API key is configured at all, which is the most common failure cause.
Full-text search of federal rulemaking dockets on Regulations.gov. Returns docket summaries: id, title, docket_type (Rulemaking or Nonrulemaking), agency_id, last_modified, and match_context (a plain-text snippet showing why the docket matched). Use the returned id with get_docket for the abstract or list_documents for its documents.
agency_id parameter lacks enum constraint; accepts free-form strings (e.g., 'EPA', 'BIS') without validation. LLMs may hallucinate invalid agency codes.
Output schemas documented only in docstrings, not as explicit JSON Schema definitions. Downstream tools cannot programmatically discover field types and structure.
Parameter constraints (page 1-20, page_size 5-250) stated in descriptions but not enforced in schema minima/maxima. Validation happens at runtime in client.py, not at tool definition.
No batch variants for tools agents might call in loops. If an agent needs to fetch multiple dockets, it must call get_docket N times sequentially.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 64 | 2026-07-28+ | v2 |
search_dockets returns 'match_context' (highlighted snippet) but does not document whether it is plain text or HTML. Client code strips HTML, but tool description does not clarify output format.