Skip to main content
Glama

federal-regulations-mcp-server

regulations_get_cfr_section

regulations_get_cfr_section
Read-onlyIdempotent

Read the codified text at a CFR location via eCFR — current or as of a past date. Answers "what does 40 CFR 50.1 say today?" and "...as of 2019-01-01?". Three locations: title + part + section for one section; title + part alone for the whole part (large parts can be very long, and their appendices are named rather than inlined; prefer a specific section when you know it); title + appendix for one appendix, passing the identifier exactly as regulations_browse_cfr emits it. eCFR retains historical versions back to roughly 2017; a date before coverage is rejected with guidance. Current single-section reads are served from a synced local mirror when available; the source is reported.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoPoint-in-time date, ISO 8601 (YYYY-MM-DD). Default current. eCFR retains historical versions back to ~2017; a date before coverage is rejected.
partNoCFR part within the title (e.g. "50"). Parts can be alphanumeric. Required unless appendix is given, where it is optional but recommended: an appendix identifier is unique within a part, not within a title, so without a part eCFR picks one of the matches. Obtain from regulations_browse_cfr or a Federal Register document's cfrReferences.
titleYesCFR title number (1–50). E.g. 40 for "Protection of Environment".
sectionNoSection identifier within the part (e.g. "50.1"). Omit to fetch the entire part — large parts can be very long; prefer a specific section when you know it. Cannot be combined with appendix.
appendixNoAppendix identifier, verbatim as eCFR writes it — the `appendix` field or the leading phrase of the `cfrCite` on a regulations_browse_cfr appendix node or search hit. It is free-form prose, not a letter: "Appendix A-1 to Part 50", "Appendix A to Subpart C of Part 4", "Schedule I to Part 789", "Special Federal Aviation Regulation No. 88". Pass the whole phrase; a short form such as "A-1" matches nothing. Cannot be combined with section.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoThe issue/point-in-time date the text reflects (ISO 8601).
partNoCFR part; null only for an appendix that hangs off a chapter, subchapter, or subtitle rather than a part.
errorNoPresent when the call failed. Absent on success.
titleNoCFR title number.
sourceNoProvenance: the synced mirror, or the live eCFR API.
cfrCiteNoAssembled cite — "40 CFR 50.1" for a section, "40 CFR 50" for a part, "Appendix A-1 to Part 50, Title 40" for an appendix (eCFR's own form, leading with the identifier this tool takes back as `appendix`).
headingNoSection, part, or appendix heading.
sectionNoSection identifier; null when a whole part or an appendix was fetched.
appendixNoAppendix identifier; null when a section or whole part was fetched.
bodyTextNoText of the section, part, or appendix, XML stripped to plain text. Paragraphs, subheadings, editorial notes, tables (one pipe-delimited line per row), figure references ("[Figure: /graphics/…]"), and the trailing source citation are kept in document order. The source citation is the bracketed Federal Register history the text ends in ("[36 FR 22384, Nov. 25, 1971, as amended at 81 FR 68276, Oct. 3, 2016]") — pass one of its FR cites to regulations_search_rules to reach the rulemaking that produced this text. Empty only where the location is a placeholder carrying nothing but its heading — "[Reserved]", or an agency variant of it.
sectionsNoPresent only when a whole part was fetched — each section in the part.
appendicesNoPresent on a whole-part fetch when the part has appendices — their identifiers and headings, without their text. A part's appendices routinely run several times the length of its sections, so they are not inlined; call this tool again with `appendix` set to one of these identifiers to read it. Absent means the part has no appendices; a single-section or appendix fetch never carries this field.
hierarchyPathNoHuman-readable hierarchy path.

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds genuine behavioral disclosures beyond that: historical coverage back to roughly 2017 with rejection-guidance behavior, and the local-mirror serving for current single-section reads with 'the source is reported.' The note that appendices are 'named rather than inlined' sets expectations about part output structure. No contradiction with the read-only annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense paragraph front-loaded with purpose in the first sentence. Every clause carries information — examples, three modes, size caveat, date coverage, mirror behavior — though the middle 'Three locations' sentence is long with embedded parentheticals. The date-coverage detail is slightly redundant with the schema's date description but is important enough to justify repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter, three-mode tool, the description covers all invocation-relevant behavior: valid parameter combinations, size caveats, appendix identifier requirements, date coverage limits and rejection behavior, and source/mirror provenance. The output schema documents return values, so the description need not explain them. The only unaddressed edge case is behavior for nonexistent CFR locations, which is a minor gap against the overall completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3 per the rubric. The description adds combinatorial meaning the schema does not explicitly express: the three valid parameter groupings (title+part+section, title+part, title+appendix) and the strategic guidance to prefer a section over a part and to pass appendix identifiers 'exactly as regulations_browse_cfr emits it.' That framing meaningfully helps an agent choose a parameter combination.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource: 'Read the codified text at a CFR location via eCFR.' Concrete example questions ('what does 40 CFR 50.1 say today?') anchor the intent. The three-location framing distinguishes it from the browsing sibling, regulations_browse_cfr, which is referenced only as the source of identifiers rather than the reader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: the three location modes, the explicit size caveat and preference ('large parts can be very long... prefer a specific section when you know it'), and the historical-date behavior with pre-2017 dates 'rejected with guidance.' It also points to regulations_browse_cfr as the identifier source, establishing a workflow. However, it never explicitly states when not to use this tool versus an alternative, so it stops short of full when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: browsing vs searching, getting specific entities (CFR sections, dockets, documents) vs listing/finding comments. No overlap or ambiguity.

Naming Consistency5/5

All tools follow the consistent 'regulations_<verb>_<object>' pattern (e.g., browse_cfr, get_docket, list_open_comments), making it easy to predict functionality.

Tool Count5/5

Seven tools is well-scoped for a regulations domain, covering discovery (search, browse, list) and retrieval (get, find) without redundancy or bloat.

Completeness5/5

The set covers the core regulatory workflow: searching rules, browsing CFR structure, retrieving specific sections, dockets, documents, and comments. No obvious gaps for read-only access.