io.github.cyanheads/federal-regulations-mcp-server

Official7 toolsLive

by cyanheads · TypeScript

Search and trace US federal rules across the Federal Register, eCFR, and Regulations.gov.

This MCP server provides tools to search and trace US federal rules across the Federal Register (proposed/final rules and notices), the eCFR (codified, point-in-time CFR full text, locally mirrored), and Regulations.gov (rulemaking dockets and public comments). It supports MCP over STDIO or Streamable HTTP.

🛠️ Key Features

Search and trace federal rules
Sources: Federal Register, eCFR, Regulations.gov
eCFR: point-in-time full text, locally mirrored
MCP access via STDIO or Streamable HTTP
7 tools

🚀 Use Cases

Finding proposed vs. final Federal Register content
Tracing a rule through codified eCFR text
Locating Regulations.gov dockets and public comments

⚡ Developer Benefits

Works with Model Context Protocol for integrating legal/regulatory lookups
Structured retrieval across three official sources
TypeScript-oriented project topics

⚠️ Limitations

Coverage is limited to the Federal Register, eCFR, and Regulations.gov described above
eCFR content is point-in-time and locally mirrored

Topics

ai-agentscyanheadsecfrfederal-registergovernmentmcpmcp-servermodel-context-protocolregulationstypescript

Captured live from the server via tools/list.

regulations_search_rules

Search the Federal Register — the daily journal of US proposed rules, final rules, notices, and presidential documents (1994–present) — filtering by full-text query, document type, agency slug, publication date range, affected CFR title and part, printed docket number, and RIN, all combined. A page cite from a CFR source note ("89 FR 49102", with its date) resolves to the documents printed on that page. The primary discovery entry point: results carry the document number (open with regulations_get_document), its citation and page range, each issuing agency with its filterable slug, printed docket numbers, Regulations.gov docket and document IDs, comment count and comment URL, whether the comment period is open, RINs, and affected CFR parts that chain into the comment and codified-text tools. A query ranks by relevance unless order says otherwise; filter-only browsing lists newest first. The Federal Register caps navigation at 50 pages and the match count at 10,000; when a result set is larger, narrow with published_after/published_before rather than paging deeper.

Parameters14

query	string	optional	Full-text search across document title and body. Omit to browse by filters alone (e.g. all EPA proposed rules in a date range).
type	array	optional	Document types to include. PRORULE=Proposed Rule, RULE=Final Rule, NOTICE=Notice, PRESDOCU=Presidential Document. Omit for all types.
agencies	array	optional	Filter to one or more agencies by Federal Register agency slug (e.g. "environmental-protection-agency", "securities-and-exchange-commission") — lowercase kebab-case, not a name or acronym. Every result lists its agencies with their slugs; if unsure, search by query and read agencies[].slug off a result. One unrecognized slug fails the whole request.
published_after	any	optional	Earliest publication date, ISO 8601 (YYYY-MM-DD), a real calendar day. Combine with published_before to window large result sets — the FR caps navigation at 50 pages.
published_before	any	optional	Latest publication date, ISO 8601 (YYYY-MM-DD), a real calendar day.
cfr_title	integer	optional	Only documents whose affected CFR parts (cfrReferences) fall in this title (1–50) — such as the title regulations_get_cfr_section just read. Alone it filters to the title; with cfr_part, to that part.
cfr_part	string	optional	Only documents whose cfrReferences list this part of cfr_title: a part number ("141") or a range ("140-143"), such as the part regulations_get_cfr_section just read; a "Part" or "pt." prefix is dropped. Requires cfr_title. A part with a letter in it ("1203a") cannot be filtered on. Unlike a query of "40 CFR 141", which matches documents that mention the part, this matches the documents whose CFR references list it.
docket_id	string	optional	Only documents carrying this docket number as the Federal Register prints it — a docketIds entry from a result here or from regulations_get_document, with or without a wrapper such as "Docket No.". Lists a docket's Federal Register documents with no REGULATIONS_GOV_API_KEY. A Regulations.gov docket ID matches only where the Federal Register prints it. Pass the complete number: a fragment ("FAA-2026") matches every docket that contains it.
rin	string	optional	Only documents carrying this Regulation Identifier Number — a regulationIdNumbers entry such as "2040-AG18", which follows one rulemaking from proposal to final rule. Pass the complete RIN: a fragment ("2040") matches every RIN that contains it.
citation	any	optional	A Federal Register page cite, "89 FR 49102" (volume FR page) — such as one from the source note that ends a regulations_get_cfr_section bodyText. Returns the documents printed on that page, usually one and sometimes a few sharing it, ordered by start page. Requires citation_date and replaces published_after/published_before. Volume 59 (1994) onward.
citation_date	any	optional	The publication date printed beside the cite in the source note (YYYY-MM-DD) — "89 FR 49102, June 11, 2024" is 2024-06-11. Required with citation; its year is the volume + 1935.
order	string	optional	Result order. Defaults to relevance with a query, newest without one. relevance without a query falls back to newest first; oldest lists the earliest publications first. Ignored with citation, whose matches come in page order.
per_page	integer	optional	Results per page (2–100, default 20). The Federal Register API treats exactly 1 as its default page size instead of returning one result.
page	integer	optional	Page number (1–50, default 1). The Federal Register serves 50 pages, so a query reaches 50 × per_page matches (5,000 at per_page 100); totalPages and nextPage in the response say how far this one goes. To reach past that, narrow with published_after/published_before rather than paging deeper.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Full-text search across document title and body. Omit to browse by filters alone (e.g. all EPA proposed rules in a date range).",
      "type": "string"
    },
    "type": {
      "description": "Document types to include. PRORULE=Proposed Rule, RULE=Final Rule, NOTICE=Notice, PRESDOCU=Presidential Document. Omit for all types.",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "PRORULE",
          "RULE",
          "NOTICE",
          "PRESDOCU"
        ]
      }
    },
    "agencies": {
      "description": "Filter to one or more agencies by Federal Register agency slug (e.g. \"environmental-protection-agency\", \"securities-and-exchange-commission\") — lowercase kebab-case, not a name or acronym. Every result lists its agencies with their slugs; if unsure, search by query and read agencies[].slug off a result. One unrecognized slug fails the whole request.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "published_after": {
      "description": "Earliest publication date, ISO 8601 (YYYY-MM-DD), a real calendar day. Combine with published_before to window large result sets — the FR caps navigation at 50 pages.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "published_before": {
      "description": "Latest publication date, ISO 8601 (YYYY-MM-DD), a real calendar day.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "cfr_title": {
      "description": "Only documents whose affected CFR parts (cfrReferences) fall in this title (1–50) — such as the title regulations_get_cfr_section just read. Alone it filters to the title; with cfr_part, to that part.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "cfr_part": {
      "description": "Only documents whose cfrReferences list this part of cfr_title: a part number (\"141\") or a range (\"140-143\"), such as the part regulations_get_cfr_section just read; a \"Part\" or \"pt.\" prefix is dropped. Requires cfr_title. A part with a letter in it (\"1203a\") cannot be filtered on. Unlike a query of \"40 CFR 141\", which matches documents that mention the part, this matches the documents whose CFR references list it.",
      "type": "string"
    },
    "docket_id": {
      "description": "Only documents carrying this docket number as the Federal Register prints it — a docketIds entry from a result here or from regulations_get_document, with or without a wrapper such as \"Docket No.\". Lists a docket's Federal Register documents with no REGULATIONS_GOV_API_KEY. A Regulations.gov docket ID matches only where the Federal Register prints it. Pass the complete number: a fragment (\"FAA-2026\") matches every docket that contains it.",
      "type": "string"
    },
    "rin": {
      "description": "Only documents carrying this Regulation Identifier Number — a regulationIdNumbers entry such as \"2040-AG18\", which follows one rulemaking from proposal to final rule. Pass the complete RIN: a fragment (\"2040\") matches every RIN that contains it.",
      "type": "string"
    },
    "citation": {
      "description": "A Federal Register page cite, \"89 FR 49102\" (volume FR page) — such as one from the source note that ends a regulations_get_cfr_section bodyText. Returns the documents printed on that page, usually one and sometimes a few sharing it, ordered by start page. Requires citation_date and replaces published_after/published_before. Volume 59 (1994) onward.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\s*(\\d{1,3})\\s*[Ff]\\.?\\s?[Rr]\\.?\\s*(\\d{1,6})\\s*$",
          "description": "Federal Register volume and page, \"89 FR 49102\"."
        }
      ]
    },
    "citation_date": {
      "description": "The publication date printed beside the cite in the source note (YYYY-MM-DD) — \"89 FR 49102, June 11, 2024\" is 2024-06-11. Required with citation; its year is the volume + 1935.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "order": {
      "description": "Result order. Defaults to relevance with a query, newest without one. relevance without a query falls back to newest first; oldest lists the earliest publications first. Ignored with citation, whose matches come in page order.",
      "type": "string",
      "enum": [
        "relevance",
        "newest",
        "oldest"
      ]
    },
    "per_page": {
      "default": 20,
      "description": "Results per page (2–100, default 20). The Federal Register API treats exactly 1 as its default page size instead of returning one result.",
      "type": "integer",
      "minimum": 2,
      "maximum": 100
    },
    "page": {
      "default": 1,
      "description": "Page number (1–50, default 1). The Federal Register serves 50 pages, so a query reaches 50 × per_page matches (5,000 at per_page 100); totalPages and nextPage in the response say how far this one goes. To reach past that, narrow with published_after/published_before rather than paging deeper.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_get_document

Fetch one Federal Register document by its FR document number — full metadata (title, type, agencies, abstract, action, effective/comment dates, RINs) plus the cross-source handles that make this a workflow server. The output carries the Regulations.gov docket ID (chain into regulations_get_docket or regulations_find_comments), the docket numbers the Federal Register prints (chain back into regulations_search_rules as docket_id), the comment count and comment URL, and the affected CFR parts (chain into regulations_get_cfr_section). Set include_full_text only when the rule body itself is needed: it returns the plain-text body as a window of up to 64,000 characters (max_chars raises it to 200,000), with the body's total length and, when text remains, the offset to resume from. Short documents return whole; major final rules run past a million characters, so page through with offset rather than reading them in one call.

Parameters4

document_number	string	required	Federal Register document number, as regulations_search_rules returns it in documentNumber: "2024-07773" from 2010 on, older and correction numbers like "98-1572", "E9-25990", or "C1-2009-30484".
include_full_text	boolean	optional	When true, inline one window of the document body as plain text (see offset and max_chars). Omitted, the body URLs alone come back unless offset or max_chars is passed; fetch full text only when you need to read the rule itself, not just its metadata and cross-links.
offset	integer	optional	Character offset into the plain-text body where the window starts (default 0). Pass the fullTextNextOffset from the previous call to read on. Implies include_full_text.
max_chars	integer	optional	Most body characters to return in this window (1–200,000, default 64,000). Implies include_full_text.

Raw schema

{
  "type": "object",
  "properties": {
    "document_number": {
      "type": "string",
      "pattern": "^[A-Za-z]?[0-9]{1,4}-[0-9]{1,6}(-[0-9]{1,6})?$",
      "description": "Federal Register document number, as regulations_search_rules returns it in documentNumber: \"2024-07773\" from 2010 on, older and correction numbers like \"98-1572\", \"E9-25990\", or \"C1-2009-30484\"."
    },
    "include_full_text": {
      "description": "When true, inline one window of the document body as plain text (see offset and max_chars). Omitted, the body URLs alone come back unless offset or max_chars is passed; fetch full text only when you need to read the rule itself, not just its metadata and cross-links.",
      "type": "boolean"
    },
    "offset": {
      "description": "Character offset into the plain-text body where the window starts (default 0). Pass the fullTextNextOffset from the previous call to read on. Implies include_full_text.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "max_chars": {
      "description": "Most body characters to return in this window (1–200,000, default 64,000). Implies include_full_text.",
      "type": "integer",
      "minimum": 1,
      "maximum": 200000
    }
  },
  "required": [
    "document_number"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_browse_cfr

Explore the codified Code of Federal Regulations via eCFR in two modes. "structure" lists all 50 titles; with a title, that title's top-level divisions (its chapters, or subtitles); and with a title and part, every section and appendix in the part, flattened and paged, each naming the subpart and subject group it sits under — the way to enumerate a part's sections without reading its text. "search" runs a full-text query across the codified CFR and returns matching sections with their hierarchy path and a snippet, one result per section, paged. Both modes accept title and part to narrow the scope. Both feed regulations_get_cfr_section. Every search result reports which corpus answered it — the synced local mirror or the live eCFR index — and what that corpus covers, in `source` and `sourceScope`.

Parameters7

mode	string	required	"structure": list titles, a title's top-level divisions, or a part's sections and appendices, to find a cite. "search": full-text search the codified CFR for sections matching a phrase.
title	integer	optional	CFR title number (1–50). Structure mode: omit to list all 50 titles; provide it alone to list the title's top-level divisions (chapters, or subtitles) — not the parts beneath them — or with part to list that part. Search mode: optional filter restricting matches to that title — e.g. 40 for environmental rules, 21 for food and drugs.
part	string	optional	CFR part within the title, in both modes — structure mode lists every section and appendix in the part, flattened and paged by page/per_page; search mode restricts matches to text inside that part. Requires title; a part on its own is rejected. Parts can be alphanumeric ("1203a", "16A") and are matched exactly once a leading "Part" or "Pt." is dropped, so pass the identifier as eCFR writes it — "58" ("Part 58" also reads as 58), not "058".
query	any	optional	Full-text search phrase (search mode, required in that mode). Ignored in structure mode.
date	any	optional	Point-in-time date, ISO 8601 (YYYY-MM-DD). Defaults to current. Structure mode uses it for the historical hierarchy, and rejects a date past the title's up-to-date date. Search mode matches only the section text in effect on that day, so a past date searches the CFR as it read then; eCFR indexes 2017-01-03 onward and rejects a date past its current index date.
page	integer	optional	1-based page of search results, or of a part's listing in structure mode (default 1); ignored by a structure listing above a part, which comes back whole. A truncation notice names the next page. Live eCFR search pages through its first 10,000 hits only, so a page starting past them is refused — narrow the query instead of paging deeper.
per_page	integer	optional	Rows per page — search results, or nodes of a part's listing in structure mode (1–50, default 20).

Raw schema

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "structure",
        "search"
      ],
      "description": "\"structure\": list titles, a title's top-level divisions, or a part's sections and appendices, to find a cite. \"search\": full-text search the codified CFR for sections matching a phrase."
    },
    "title": {
      "description": "CFR title number (1–50). Structure mode: omit to list all 50 titles; provide it alone to list the title's top-level divisions (chapters, or subtitles) — not the parts beneath them — or with part to list that part. Search mode: optional filter restricting matches to that title — e.g. 40 for environmental rules, 21 for food and drugs.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "part": {
      "description": "CFR part within the title, in both modes — structure mode lists every section and appendix in the part, flattened and paged by page/per_page; search mode restricts matches to text inside that part. Requires title; a part on its own is rejected. Parts can be alphanumeric (\"1203a\", \"16A\") and are matched exactly once a leading \"Part\" or \"Pt.\" is dropped, so pass the identifier as eCFR writes it — \"58\" (\"Part 58\" also reads as 58), not \"058\".",
      "type": "string"
    },
    "query": {
      "description": "Full-text search phrase (search mode, required in that mode). Ignored in structure mode.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "minLength": 2,
          "description": "Search phrase, at least 2 characters."
        }
      ]
    },
    "date": {
      "description": "Point-in-time date, ISO 8601 (YYYY-MM-DD). Defaults to current. Structure mode uses it for the historical hierarchy, and rejects a date past the title's up-to-date date. Search mode matches only the section text in effect on that day, so a past date searches the CFR as it read then; eCFR indexes 2017-01-03 onward and rejects a date past its current index date.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "page": {
      "default": 1,
      "description": "1-based page of search results, or of a part's listing in structure mode (default 1); ignored by a structure listing above a part, which comes back whole. A truncation notice names the next page. Live eCFR search pages through its first 10,000 hits only, so a page starting past them is refused — narrow the query instead of paging deeper.",
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    },
    "per_page": {
      "default": 20,
      "description": "Rows per page — search results, or nodes of a part's listing in structure mode (1–50, default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "required": [
    "mode"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_get_cfr_section

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, with its Authority and Source notes, an index of its sections, and the names of its appendices; title + appendix for one appendix, passing the identifier exactly as regulations_browse_cfr emits it. A section can be written as people cite it — "61", "§ 141.61", "141.61(c)", or the full cite "40 CFR 141.61" in part 141 all read 40 CFR 141.61 — and a part as "Part 141"; the response names the identifier it read. Text comes back as a window of up to 64,000 characters (max_chars raises it to 200,000) with the total length and, when text remains, the offset to resume from; whole parts run to millions of characters, so page with offset or read a single section. eCFR retains historical versions from 2017 through the title's up-to-date date; a date outside that window is rejected with the window named. Current single-section reads are served from a synced local mirror when it holds the title's latest eCFR issue; the source is reported.

Parameters7

title	integer	required	CFR title number (1–50). E.g. 40 for "Protection of Environment".
part	string	optional	CFR part within the title (e.g. "50"). Parts can be alphanumeric; a leading "Part" or "Pt." is dropped ("Part 141" reads part 141). 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.
section	any	optional	Section within the part, normally written part.section as eCFR identifies it ("141.61"). Also accepted: the number alone ("61" in part 141), a leading "§" or "Sec.", a paragraph cite ("141.61(c)"), which reads the whole section, and the full cite this tool returns as cfrCite ("40 CFR 141.61", "14 CFR 241 § 25"), whose title has to match title. Identifiers eCFR writes differently are read as given — 14 CFR 241 numbers its sections "25" and "1-1". Omit to fetch the entire part. Cannot be combined with appendix.
appendix	any	optional	Appendix 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.
date	any	optional	Point-in-time date, ISO 8601 (YYYY-MM-DD). Default current. eCFR serves 2017-01-01 through the title's up-to-date date, usually a few days behind today; a date outside that window is rejected, naming the window.
offset	integer	optional	Character offset into the text where the window starts (default 0). Pass bodyTextNextOffset from the previous call to read on, or a sections[].offset from a whole-part read to jump to that section.
max_chars	integer	optional	Most text characters to return in this window (1–200,000, default 64,000).

Raw schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "CFR title number (1–50). E.g. 40 for \"Protection of Environment\"."
    },
    "part": {
      "description": "CFR part within the title (e.g. \"50\"). Parts can be alphanumeric; a leading \"Part\" or \"Pt.\" is dropped (\"Part 141\" reads part 141). 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.",
      "type": "string"
    },
    "section": {
      "description": "Section within the part, normally written part.section as eCFR identifies it (\"141.61\"). Also accepted: the number alone (\"61\" in part 141), a leading \"§\" or \"Sec.\", a paragraph cite (\"141.61(c)\"), which reads the whole section, and the full cite this tool returns as cfrCite (\"40 CFR 141.61\", \"14 CFR 241 § 25\"), whose title has to match title. Identifiers eCFR writes differently are read as given — 14 CFR 241 numbers its sections \"25\" and \"1-1\". Omit to fetch the entire part. Cannot be combined with appendix.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "description": "Section identifier (e.g. \"50.1\")."
        }
      ]
    },
    "appendix": {
      "description": "Appendix 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.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "description": "Appendix identifier (e.g. \"Appendix A-1 to Part 50\")."
        }
      ]
    },
    "date": {
      "description": "Point-in-time date, ISO 8601 (YYYY-MM-DD). Default current. eCFR serves 2017-01-01 through the title's up-to-date date, usually a few days behind today; a date outside that window is rejected, naming the window.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "offset": {
      "description": "Character offset into the text where the window starts (default 0). Pass bodyTextNextOffset from the previous call to read on, or a sections[].offset from a whole-part read to jump to that section.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "max_chars": {
      "description": "Most text characters to return in this window (1–200,000, default 64,000).",
      "type": "integer",
      "minimum": 1,
      "maximum": 200000
    }
  },
  "required": [
    "title"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_get_docket

Pull a rulemaking docket from Regulations.gov by docket ID (e.g. "EPA-HQ-OAR-2025-0194") — the docket's metadata (title, agency, RIN, abstract) and the documents filed in it (NPRM, final rule, supporting materials). The docket is the folder holding a rule's whole paper trail; each returned document's objectId feeds regulations_find_comments. A docket often contains hundreds of supporting materials — filter document_types to "Proposed Rule"/"Rule" to find the rule documents themselves. Requires REGULATIONS_GOV_API_KEY (free at https://api.data.gov/signup/); the Federal Register and eCFR tools work without it.

Parameters4

docket_id	string	required	Regulations.gov docket ID (e.g. "EPA-HQ-OAR-2025-0194"). Obtain from regulationsGovDocketId on a regulations_search_rules or regulations_list_open_comments row, or docketId from regulations_get_document. The printed docketIds on those tools are not always Regulations.gov IDs ("REG-101355-26" is the IRS's own number for docket IRS-2026-0925).
document_types	array	optional	Filter the docket's documents to these types. Omit for all. A docket often contains hundreds of "Supporting & Related Material" items — filter to "Proposed Rule"/"Rule" to find the rule documents.
per_page	integer	optional	Documents per page (5–250, default 25). Regulations.gov requires a minimum page size of 5.
page	integer	optional	Page number (1–40, default 1). Regulations.gov serves 40 pages, so a docket listing reaches 40 × per_page documents (10,000 at per_page 250); totalPages and nextPage in the response say how far this one goes. Beyond that, narrow with document_types.

Raw schema

{
  "type": "object",
  "properties": {
    "docket_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "description": "Regulations.gov docket ID (e.g. \"EPA-HQ-OAR-2025-0194\"). Obtain from regulationsGovDocketId on a regulations_search_rules or regulations_list_open_comments row, or docketId from regulations_get_document. The printed docketIds on those tools are not always Regulations.gov IDs (\"REG-101355-26\" is the IRS's own number for docket IRS-2026-0925)."
    },
    "document_types": {
      "description": "Filter the docket's documents to these types. Omit for all. A docket often contains hundreds of \"Supporting & Related Material\" items — filter to \"Proposed Rule\"/\"Rule\" to find the rule documents.",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "Proposed Rule",
          "Rule",
          "Notice",
          "Supporting & Related Material",
          "Other"
        ]
      }
    },
    "per_page": {
      "default": 25,
      "description": "Documents per page (5–250, default 25). Regulations.gov requires a minimum page size of 5.",
      "type": "integer",
      "minimum": 5,
      "maximum": 250
    },
    "page": {
      "default": 1,
      "description": "Page number (1–40, default 1). Regulations.gov serves 40 pages, so a docket listing reaches 40 × per_page documents (10,000 at per_page 250); totalPages and nextPage in the response say how far this one goes. Beyond that, narrow with document_types.",
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    }
  },
  "required": [
    "docket_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_find_comments

Fetch public comments on a Federal Register document or a Regulations.gov docket — the unique corpus of what citizens and organizations actually submitted. Provide exactly one targeting parameter: docket_id (all comments in a docket, broadest), document_object_id (comments on one document, by its object ID or document ID), fr_document_number (convenience — resolves the FR number to the Regulations.gov document carrying it), or comment_id (one comment's full detail and attachments). A list narrows by comment text with search_term (each hit then carries the matching passages) and by posted date with posted_after/posted_before. The list endpoint returns no body text or attachment info — call with comment_id to read a comment's body. When a comment's real content is a PDF/DOCX attachment, the body is a stub and attachmentOnly is true; the attachment download URLs are returned. Requires REGULATIONS_GOV_API_KEY (free at https://api.data.gov/signup/).

Parameters9

docket_id	string	optional	Fetch all comments in a docket by Regulations.gov docket ID (e.g. "EPA-HQ-OAR-2025-0194") — regulationsGovDocketId on a regulations_search_rules or regulations_list_open_comments row, or docketId from regulations_get_document, not an entry of the printed docketIds. Broadest scope. Exactly one of docket_id / document_object_id / fr_document_number / comment_id is required — supplying two is rejected, not resolved by precedence.
document_object_id	string	optional	Fetch comments on one specific Regulations.gov document, by either handle: its object ID, 16 hex characters (e.g. "0900006485883ec6", the objectId in regulations_get_docket's documents), or its document ID (e.g. "EPA-HQ-OW-2022-0114-0027", the regulationsGovDocumentId from regulations_get_document). Comments usually attach to the docket's primary (proposed-rule) document. Mutually exclusive with the other three targeting parameters.
fr_document_number	any	optional	Convenience: fetch comments on the Regulations.gov document carrying a Federal Register number (e.g. "2023-05471"; older numbers like "E9-25990" too). A Regulations.gov document ID ("EPA-HQ-OW-2022-0114-0027") is not an FR number; pass it as document_object_id. Saves a get_document → get_docket hop. A document that is not on Regulations.gov — a presidential document, for one — answers not_found. Mutually exclusive with the other three targeting parameters.
comment_id	string	optional	Fetch one comment's full detail and attachments by its Regulations.gov comment ID (e.g. "EPA-HQ-OAR-2025-0194-31102"). Use to read a single comment's body after finding it in a list. Mutually exclusive with the other three targeting parameters — pass it alone, not alongside the docket it came from — and takes none of the list filters.
search_term	string	optional	List mode: keep only comments whose text matches, as Regulations.gov full-text search reads it — stemmed, so "flaring" also matches "flare" and "flares". Each hit then carries highlightedContent, the passages that matched.
posted_after	any	optional	List mode: earliest posted date, inclusive, ISO 8601 (YYYY-MM-DD), a real calendar day. Pair with posted_before to take a high-volume set one window at a time.
posted_before	any	optional	List mode: latest posted date, inclusive, ISO 8601 (YYYY-MM-DD), a real calendar day. The same date as posted_after selects that one day.
per_page	integer	optional	Comments per page (5–250, default 25). Regulations.gov requires a minimum page size of 5.
page	integer	optional	Page number (1–40, default 1). Regulations.gov serves 40 pages, so a list reaches 40 × per_page comments (10,000 at per_page 250); totalPages and nextPage in the response say how far this one goes. To reach past that, take the set one posted_after/posted_before window at a time.

Raw schema

{
  "type": "object",
  "properties": {
    "docket_id": {
      "description": "Fetch all comments in a docket by Regulations.gov docket ID (e.g. \"EPA-HQ-OAR-2025-0194\") — regulationsGovDocketId on a regulations_search_rules or regulations_list_open_comments row, or docketId from regulations_get_document, not an entry of the printed docketIds. Broadest scope. Exactly one of docket_id / document_object_id / fr_document_number / comment_id is required — supplying two is rejected, not resolved by precedence.",
      "type": "string"
    },
    "document_object_id": {
      "description": "Fetch comments on one specific Regulations.gov document, by either handle: its object ID, 16 hex characters (e.g. \"0900006485883ec6\", the objectId in regulations_get_docket's documents), or its document ID (e.g. \"EPA-HQ-OW-2022-0114-0027\", the regulationsGovDocumentId from regulations_get_document). Comments usually attach to the docket's primary (proposed-rule) document. Mutually exclusive with the other three targeting parameters.",
      "type": "string"
    },
    "fr_document_number": {
      "description": "Convenience: fetch comments on the Regulations.gov document carrying a Federal Register number (e.g. \"2023-05471\"; older numbers like \"E9-25990\" too). A Regulations.gov document ID (\"EPA-HQ-OW-2022-0114-0027\") is not an FR number; pass it as document_object_id. Saves a get_document → get_docket hop. A document that is not on Regulations.gov — a presidential document, for one — answers not_found. Mutually exclusive with the other three targeting parameters.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^[A-Za-z]?[0-9]{1,4}-[0-9]{1,6}(-[0-9]{1,6})?$",
          "description": "Federal Register document number (e.g. \"2023-05471\", \"E9-25990\")."
        }
      ]
    },
    "comment_id": {
      "description": "Fetch one comment's full detail and attachments by its Regulations.gov comment ID (e.g. \"EPA-HQ-OAR-2025-0194-31102\"). Use to read a single comment's body after finding it in a list. Mutually exclusive with the other three targeting parameters — pass it alone, not alongside the docket it came from — and takes none of the list filters.",
      "type": "string"
    },
    "search_term": {
      "description": "List mode: keep only comments whose text matches, as Regulations.gov full-text search reads it — stemmed, so \"flaring\" also matches \"flare\" and \"flares\". Each hit then carries highlightedContent, the passages that matched.",
      "type": "string"
    },
    "posted_after": {
      "description": "List mode: earliest posted date, inclusive, ISO 8601 (YYYY-MM-DD), a real calendar day. Pair with posted_before to take a high-volume set one window at a time.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "posted_before": {
      "description": "List mode: latest posted date, inclusive, ISO 8601 (YYYY-MM-DD), a real calendar day. The same date as posted_after selects that one day.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "per_page": {
      "default": 25,
      "description": "Comments per page (5–250, default 25). Regulations.gov requires a minimum page size of 5.",
      "type": "integer",
      "minimum": 5,
      "maximum": 250
    },
    "page": {
      "default": 1,
      "description": "Page number (1–40, default 1). Regulations.gov serves 40 pages, so a list reaches 40 × per_page comments (10,000 at per_page 250); totalPages and nextPage in the response say how far this one goes. To reach past that, take the set one posted_after/posted_before window at a time.",
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

regulations_list_open_comments

List Federal Register documents currently open for public comment, sorted by closing date (soonest first) across the whole open window, filterable by document type, agency slug, and topic. "What can I still weigh in on?" Covers proposed rules and the final rules that take comment (direct final and interim final rules) by default; add NOTICE for the much larger set of notices with comment periods. Runs on the Federal Register's open-comment window and needs no key: each row carries its Regulations.gov docket and document IDs, comment count, and comment URL from the Federal Register document's embedded Regulations.gov info. Open one row with regulations_get_document for the full document, or pull the comments with regulations_find_comments (which, like regulations_get_docket, needs REGULATIONS_GOV_API_KEY).

Parameters6

query	string	optional	Full-text filter across open documents. Omit to list every document currently open for comment.
type	array	optional	Document types to include: PRORULE (proposed rules), RULE (final rules that request comment, including direct final and interim final rules), NOTICE (information-collection and other notices with comment periods — a much larger set). Default, and when empty: ["PRORULE", "RULE"].
agencies	array	optional	Filter to one or more agencies by Federal Register agency slug (e.g. "environmental-protection-agency") — lowercase kebab-case, not a name or acronym. Every row lists its agencies with their slugs; read agencies[].slug off a row here or in regulations_search_rules. One unrecognized slug fails the whole request.
closing_before	any	optional	Only documents whose comment period closes on or before this date, ISO 8601 (YYYY-MM-DD), a real calendar day. Use to find deadlines you need to act on soon.
per_page	integer	optional	Documents per page (1–100, default 20).
page	integer	optional	Page number, default 1. Pages run over the whole open window in closing-date order; totalPages and nextPage in the response say how far it goes.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Full-text filter across open documents. Omit to list every document currently open for comment.",
      "type": "string"
    },
    "type": {
      "description": "Document types to include: PRORULE (proposed rules), RULE (final rules that request comment, including direct final and interim final rules), NOTICE (information-collection and other notices with comment periods — a much larger set). Default, and when empty: [\"PRORULE\", \"RULE\"].",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "PRORULE",
          "RULE",
          "NOTICE"
        ]
      }
    },
    "agencies": {
      "description": "Filter to one or more agencies by Federal Register agency slug (e.g. \"environmental-protection-agency\") — lowercase kebab-case, not a name or acronym. Every row lists its agencies with their slugs; read agencies[].slug off a row here or in regulations_search_rules. One unrecognized slug fails the whole request.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "closing_before": {
      "description": "Only documents whose comment period closes on or before this date, ISO 8601 (YYYY-MM-DD), a real calendar day. Use to find deadlines you need to act on soon.",
      "anyOf": [
        {
          "type": "string",
          "const": ""
        },
        {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "ISO 8601 date (YYYY-MM-DD)."
        }
      ]
    },
    "per_page": {
      "default": 20,
      "description": "Documents per page (1–100, default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "page": {
      "default": 1,
      "description": "Page number, default 1. Pages run over the whole open window in closing-date order; totalPages and nextPage in the response say how far it goes.",
      "type": "integer",
      "minimum": 1,
      "maximum": 10000
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

README.md22 KBView on GitHub

@cyanheads/federal-regulations-mcp-server

Search and trace US federal rules across the Federal Register (proposed/final rules and notices), the eCFR (codified, point-in-time CFR full text, locally mirrored), and Regulations.gov (rulemaking dockets and public comments) via MCP. STDIO or Streamable HTTP.

7 Tools • 2 Resources

MCP SDK TypeScript

Public Hosted Server: https://federal-regulations.caseyjhand.com/mcp

Overview

US federal regulatory law from three official sources: the Federal Register (proposed rules, final rules, and notices), the eCFR (codified CFR text, current or as of a past date), and Regulations.gov (rulemaking dockets and public comments). Search rules, trace a document from proposal through its comments to the codified text, and read CFR sections. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Tool	Description
`regulations_search_rules`	Search Federal Register proposed rules, final rules, notices, and presidential documents by query, type, agency, date range, CFR part, docket number, and RIN, or resolve a page cite to its document
`regulations_get_document`	Fetch one Federal Register document by number, with the docket IDs, CFR parts, citation, comment count, and comment URL that chain into other tools
`regulations_browse_cfr`	List CFR titles, a title's chapters, or every section and appendix in a part, or full-text-search the codified CFR
`regulations_get_cfr_section`	Read codified CFR text for a section, whole part, or appendix, current or as of a past date
`regulations_get_docket`	Pull a rulemaking docket and its filed documents from Regulations.gov (key required)
`regulations_find_comments`	Fetch public comments on a document or docket, or one comment's full body and attachments (key required)
`regulations_list_open_comments`	List documents currently open for public comment, soonest closing first

Resources

Resource	Description
`regulations://document/{documentNumber}`	One Federal Register document's metadata and cross-source handles
`regulations://cfr/{title}/{part}/{section}`	Codified text of a current CFR section

Both resources mirror a tool (regulations_get_document, regulations_get_cfr_section), so tool-only clients lose nothing.

Capability reference

`regulations_search_rules` _tool

Optional full-text query, filtered by type (PRORULE / RULE / NOTICE / PRESDOCU), agencies (Federal Register slugs such as environmental-protection-agency, not names or acronyms), published_after / published_before, cfr_title + cfr_part (a part number or range such as 140-143; cfr_part needs cfr_title, else title_required_for_part), docket_id (a docket number as the Federal Register prints it), and rin, all combined; per_page 2–100 (default 20), page 1–50
citation ("89 FR 49102") with citation_date (the date its source note prints beside it) returns the documents printed on that page, in page order, volume 59 (1994) onward. A cite missing its date, or combined with the date window, fails with citation_incomplete; a volume before 59 or a date from another year fails with citation_out_of_range. When no document spans the page, the notice gives that day's page range
Each result carries documentNumber, citation / startPage / endPage, agencies[].slug, the printed docketIds, regulationsGovDocketId and regulationsGovDocumentId, commentCount, commentUrl, commentsCloseOn with commentPeriodOpen (open through 11:59 PM Eastern on the close date), regulationIdNumbers, and cfrReferences for the follow-up tools. totalPages and nextPage page the results. The Federal Register serves 50 pages, so truncated marks a set larger than 50 × per_page (1,000 at the default, 5,000 at 100); narrow the date window rather than paging deeper. totalCount stops at 10,000, which means at least that many. A window whose start falls after its end fails with date_range_inverted, and invalid_filter names a rejected parameter

`regulations_get_document` _tool

document_number in any form the Federal Register issues: 2024-07773 from 2010 on, and older and correction numbers such as 98-1572, E9-25990, or C1-2009-30484; include_full_text adds the plain-text body as one window of max_chars (default 64,000, max 200,000) starting at offset, and passing either of those implies it
Returns metadata plus the handles other tools take: the Regulations.gov docketId and regulationsGovDocumentId, the printed docketIds, citation / startPage / endPage, commentCount, commentUrl, commentPeriodOpen, and cfrReferences. With text, fullTextLength and fullTextNextOffset (present while text remains) page the body; a major final rule runs past a million characters

`regulations_browse_cfr` _tool

mode: "structure" lists the 50 titles, a title's top-level divisions, or, with title + part, every section and appendix in the part with its subpart and subjectGroup; mode: "search" full-text-searches the codified CFR and requires query. title, part (needs title), and a point-in-time date scope both modes, and per_page 1–50 (default 20) pages search results and part listings
Search rows carry cfrCite, heading, hierarchyPath, and excerpt, one per section. source (mirror / live) and sourceScope name the corpus that answered and what it covers, and countBasis says whether totalCount counts sections or section_versions; live search reaches eCFR's first 10,000 hits only (page_out_of_window past them)

`regulations_get_cfr_section` _tool

One section (title + part + section), a whole part (section omitted), or one appendix (appendix, verbatim as regulations_browse_cfr emits it, e.g. Appendix A-1 to Part 50). section also takes cites as people write them ("61", "§ 141.61", "141.61(c)") and the cfrCite the server returns ("40 CFR 141.61", "14 CFR 241 § 25"; a cite naming another title fails with conflicting_title), part takes "Part 141", and date reads text from 2017-01-01 through the title's up-to-date date
Text comes back as one bodyText window (max_chars default 64,000, max 200,000, from offset), paged by bodyTextLength and bodyTextNextOffset. A whole-part read adds a sections[] index with each section's offset and names its appendices without their text; source (mirror / live) reports provenance
A whole-part read also returns the part's heading, authority, sourceNote, and notes, and each sections[] entry carries the Authority or Source its subpart or subject group states for it
Superscripts read ^x and subscripts _x (3 × 10^−8, CO_{2}e), footnote markers [n], and diacritics and overlines are combining marks (x̄)

`regulations_get_docket` _tool · key required

docket_id, the Regulations.gov docket ID (e.g. EPA-HQ-OAR-2025-0194) — regulationsGovDocketId on a search or open-comments row, docketId from regulations_get_document, not a printed docketIds entry; document_types filters to Proposed Rule, Rule, Notice, Supporting & Related Material, or Other; per_page 5–250 (default 25), page 1–40
Returns the docket's metadata, documentCount, and documents[], each with an objectId for regulations_find_comments, a frDocNum back to regulations_get_document, and commentPeriodOpen as Regulations.gov reports it. totalPages and nextPage page the documents; Regulations.gov serves 40 pages, so truncated marks a docket larger than 40 × per_page (10,000 at 250)

`regulations_find_comments` _tool · key required

Exactly one of docket_id, document_object_id, fr_document_number, or comment_id; list scopes take per_page 5–250 (default 25) and page 1–40
document_object_id takes an object ID (0900006485883ec6) or a document ID (EPA-HQ-OW-2022-0114-0027). fr_document_number resolves to the Regulations.gov document carrying that exact number and answers not_found when none does
Lists narrow by comment text with search_term, and each hit then carries highlightedContent, the matched passages. posted_after / posted_before set an inclusive posted-date window. A backwards window fails with date_range_inverted, and filters passed with comment_id fail with filter_requires_list_mode
mode is list or detail. Lists return comment summaries without body text. comment_id returns the body, submitter, receivedDate, postmarkDate, duplicateComments (above 1 marks a mass-mail campaign record), and attachments, with attachmentOnly: true when the substance is in a PDF/DOCX file. Lists carry totalPages and nextPage; truncated marks a set larger than the 40 pages Regulations.gov serves reach (40 × per_page, 10,000 at 250), and posted-date windows take it one slice at a time

`regulations_list_open_comments` _tool

Optional query, type (PRORULE, RULE, NOTICE; default ["PRORULE", "RULE"]), agencies (Federal Register slugs), and closing_before; per_page 1–100 (default 20)
Rows sort by closing date, soonest first, and carry commentsCloseOn, daysRemaining, documentNumber, the printed docketIds, regulationsGovDocketId and regulationsGovDocumentId, commentCount, and commentUrl. asOf is today's date in Eastern time, so a document stays listed through its close day. totalPages and nextPage page the window; truncated means the Federal Register's 10,000-document limit was reached
Keyless. keyed reports whether REGULATIONS_GOV_API_KEY is set, which regulations_get_docket and regulations_find_comments need to follow up on a row

`regulations://document/{documentNumber}` _resource

documentNumber in any Federal Register form (2024-07773, 98-1572, E9-25990); the payload is regulations_get_document's without the body text
docketId, regulationsGovDocumentId, the printed docketIds, cfrReferences, citation, commentCount, and commentUrl chain into the search, comment, and CFR tools

`regulations://cfr/{title}/{part}/{section}` _resource

Sections only, at the current date and the tool's default 64,000-character window; the part and section segments resolve the way the tool resolves them ("Part 141"; "61", "§ 141.61", "40 CFR 141.61")
source (mirror / live) reports provenance. bodyTextNextOffset marks a section longer than the window; read the rest through regulations_get_cfr_section with offset

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Federal Register / eCFR / Regulations.gov-specific:

One workflow over three official sources: the agent calls regulatory verbs (search_rules, get_cfr_section, find_comments) rather than three API clients
Cross-source stitching: every Federal Register document surfaces its docket ID and CFR-part handles, which feed the proposal → comments → final rule → codified text trace
Keyless core: the five Federal Register and eCFR tools need no key. regulations_get_docket and regulations_find_comments need REGULATIONS_GOV_API_KEY (free at api.data.gov/signup, 1,000 requests/hour) and fail with auth_required, naming the variable and signup URL, when it is missing or rejected
Locally mirrored codified CFR: the eCFR syncs into embedded SQLite + FTS5 for exact-cite reads and full-text search, and falls back to the live API for historical dates, whole parts, appendices, titles outside the mirror, and titles eCFR has re-issued since the mirror last synced them
A 45-second budget per request, shared by every upstream call, retry, and backoff, so a stalled source answers with upstream_unavailable inside a client's timeout

Agent-friendly output:

Provenance: source: "mirror" | "live" on every CFR read, plus a sourceScope line on search naming what the corpus covers
Honest paging: totalPages and nextPage say how far a list goes, a page past the end names the last page instead of reading as "nothing matched", and matches beyond the Federal Register's 50 pages or Regulations.gov's 40 surface through truncated and notice, never as silently dropped rows
Attachment-aware comments: attachmentOnly flags a comment whose substance is a file, with the download URLs

Getting started

Public Hosted Instance

A public instance is available at https://federal-regulations.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

json

{
  "mcpServers": {
    "federal-regulations-mcp-server": {
      "type": "streamable-http",
      "url": "https://federal-regulations.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file. REGULATIONS_GOV_API_KEY enables the docket and comment tools; omit it to run the keyless Federal Register and eCFR tools alone.

json

{
  "mcpServers": {
    "federal-regulations-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/federal-regulations-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "REGULATIONS_GOV_API_KEY": "your-key-here"
      }
    }
  }
}

Or with npx (no Bun required):

json

{
  "mcpServers": {
    "federal-regulations-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/federal-regulations-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "REGULATIONS_GOV_API_KEY": "your-key-here"
      }
    }
  }
}

Or with Docker:

json

{
  "mcpServers": {
    "federal-regulations-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "-e", "REGULATIONS_GOV_API_KEY=your-key-here",
        "ghcr.io/cyanheads/federal-regulations-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

Bun v1.4.0 or higher (or Node.js v24+).
Optional: a free api.data.gov key for the Regulations.gov tools.

Installation

Clone the repository:

git clone https://github.com/cyanheads/federal-regulations-mcp-server.git

Navigate into the directory:

cd federal-regulations-mcp-server

Install dependencies:

bun install

Configure environment:

cp .env.example .env
# optionally set REGULATIONS_GOV_API_KEY

Configuration

Variable	Description	Default
`REGULATIONS_GOV_API_KEY`	api.data.gov key for `regulations_get_docket` and `regulations_find_comments`.	none
`FEDERAL_REGISTER_BASE_URL`	Federal Register API v1 base URL.	`https://www.federalregister.gov/api/v1`
`ECFR_BASE_URL`	eCFR API base URL.	`https://www.ecfr.gov/api`
`REGULATIONS_GOV_BASE_URL`	Regulations.gov API v4 base URL.	`https://api.regulations.gov/v4`
`ECFR_MIRROR_PATH`	Path to the eCFR SQLite mirror database.	`./data/ecfr-mirror.sqlite`
`ECFR_MIRROR_REFRESH_CRON`	Cron expression for an in-process mirror refresh (HTTP transport only), e.g. `0 4 * * 0`. Each run re-harvests every configured title in full.	none (no job)
`ECFR_MIRROR_TITLES`	Comma-separated CFR titles to mirror (e.g. `21,40`). Reads and searches outside the set, and all-titles searches, go to the live eCFR API.	all 50 titles
`MCP_TRANSPORT_TYPE`	Transport: `stdio` or `http`.	`stdio`
`MCP_HTTP_PORT`	HTTP server port.	`3010`
`MCP_AUTH_MODE`	Authentication: `none`, `jwt`, or `oauth`.	`none`
`MCP_LOG_LEVEL`	Log level (`debug`, `info`, `warning`, `error`, etc.).	`info`
`STORAGE_PROVIDER_TYPE`	Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1`.	`in-memory`
`OTEL_ENABLED`	Enable OpenTelemetry.	`false`

See .env.example for the full list of optional overrides.

Running the server

Local development

Build and run:

# One-time build
bun run rebuild

# Run the built server
bun run start:stdio
# or
bun run start:http

Build or refresh the eCFR mirror (out of band and idempotent; the CFR tools use the live eCFR API until the first build completes):

bun run mirror:init      # full build, resumable (scope with ECFR_MIRROR_TITLES)
bun run mirror:refresh   # re-harvest every configured title against the latest eCFR issues
bun run mirror:verify    # report row counts and the last-synced issue date

Run checks and tests:

bun run devcheck   # Lint, format, typecheck, security, changelog sync
bun run test       # Vitest test suite

Docker

docker build -t federal-regulations-mcp-server .
docker run --rm -e REGULATIONS_GOV_API_KEY=your-key -p 3010:3010 federal-regulations-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/federal-regulations-mcp-server. Build the mirror inside a running container with docker exec <container> bun run mirror:init, and mount a volume over /usr/src/app/data so it survives recreation. OpenTelemetry peer dependencies are installed by default; build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Directory	Purpose
`src/index.ts`	`createApp()` entry point: registers tools and resources, inits the three services, and schedules the mirror refresh when `ECFR_MIRROR_REFRESH_CRON` is set.
`src/config`	Server-specific environment variable parsing and validation with Zod.
`src/mcp-server/tools`	Tool definitions (`.tool.ts`), the seven `regulations_` tools.
`src/mcp-server/resources`	Resource definitions (`*.resource.ts`), the document and CFR-section resources.
`src/services/federal-register`	Federal Register API v1 client (keyless).
`src/services/ecfr`	eCFR API client (keyless): versioner, structure, search, section XML parsing, and cite resolution.
`src/services/ecfr-mirror`	eCFR codified-text mirror (SQLite + FTS5) and the opt-in refresh job.
`src/services/regulations-gov`	Regulations.gov v4 client (`X-Api-Key`): dockets and comments.
`src/services`	Shared request budget, text windowing, character-reference decoding, and upstream-failure handling.
`scripts/ecfr-mirror-*.ts`	Out-of-band mirror lifecycle: `init`, `refresh`, `verify`.
`tests/`	Unit and integration tests mirroring `src/`.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

Handlers throw, framework catches — no try/catch in tool logic
Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
Register new tools and resources via the barrels in src/mcp-server/*/definitions/index.ts
Wrap external API calls: validate raw → normalize to the domain type → return the output schema; never fabricate missing upstream fields

Data disclaimer

eCFR content is "authoritative but unofficial" per the Office of the Federal Register, not the official legal edition of the Code of Federal Regulations; verify against govinfo.gov for legal research. This server is not affiliated with or endorsed by the Office of the Federal Register, the Government Publishing Office, or the General Services Administration.

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Install

Tools (7)

regulations_search_rulesregulations_get_documentregulations_browse_cfrregulations_get_cfr_sectionregulations_get_docketregulations_find_commentsregulations_list_open_comments

Configuration

Environment variables

REGULATIONS_GOV_API_KEYsecret

api.data.gov key for the Regulations.gov tools (get_docket, find_comments). Free at https://api.data.gov/signup/. The Federal Register and eCFR tools work without it.

MCP_LOG_LEVELdefault info

Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

MCP_TRANSPORT_TYPEdefault http

Selects the HTTP transport.

MCP_HTTP_HOSTdefault 127.0.0.1

The hostname for the HTTP server.

MCP_HTTP_PORTdefault 3010

The port to run the HTTP server on.

MCP_HTTP_ENDPOINT_PATHdefault /mcp

The endpoint path for the MCP server.

MCP_AUTH_MODEdefault none

Authentication mode to use: 'none', 'jwt', or 'oauth'.

ECFR_MIRROR_REFRESH_CRON

Cron expression for an in-process eCFR mirror refresh (e.g. '0 4 * * 0'). Unset registers no job. Each run re-harvests every configured title in full, and a tick is skipped until mirror:init has completed once.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "federal-regulations-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/federal-regulations-mcp-server@0.5.3"
      ],
      "env": {
        "REGULATIONS_GOV_API_KEY": "<YOUR_REGULATIONS_GOV_API_KEY>",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

regulations_search_rules

regulations_get_document

regulations_browse_cfr

regulations_get_cfr_section

regulations_get_docket

regulations_find_comments

regulations_list_open_comments

@cyanheads/federal-regulations-mcp-server

Overview

Tools

Resources

Capability reference

regulations_search_rules tool

regulations_get_document tool

regulations_browse_cfr tool

regulations_get_cfr_section tool

regulations_get_docket tool · key required

regulations_find_comments tool · key required

regulations_list_open_comments tool

regulations://document/{documentNumber} resource

regulations://cfr/{title}/{part}/{section} resource

Features

Getting started

Public Hosted Instance

Self-Hosted / Local

Prerequisites

Installation

Configuration

Running the server

Local development

Docker

Project structure

Development guide

Data disclaimer

Contributing

License

Install

Configuration

Related servers

`regulations_search_rules` _tool

`regulations_get_document` _tool

`regulations_browse_cfr` _tool

`regulations_get_cfr_section` _tool

`regulations_get_docket` _tool · key required

`regulations_find_comments` _tool · key required

`regulations_list_open_comments` _tool

`regulations://document/{documentNumber}` _resource

`regulations://cfr/{title}/{part}/{section}` _resource