Search Us Statutes
search_us_statutesRead-only
Find legal answers across all US jurisdictions: federal and state statutes, regulations, constitutions, and court rules. Returns ranked sections with citations and official links.
Instructions
Semantic + keyword search across US primary law: the United States Code (USC), the Code of Federal Regulations (CFR), and all 50 states' statutes, regulations, constitutions and court rules. Use for any 'what does the law say' question. Filter by corpusType and titleNumber. Returns sections with citation, hierarchy and official source links. The returned act_id (e.g. 'USC_T42_C21_S1983') feeds every other statute tool -- do not hand-build one, they usually 404.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | Restrict to specific state statutory codes, e.g. `tx_pe` for the Texas Penal Code. Values are the `actId`s from list_statute_divisions. List allowed, across states. The only way to scope below a whole jurisdiction: `state=tx` alone searches all ~15 Texas codes. | |
| part | No | One or more parts within a title, e.g. `240` for 17 C.F.R. Part 240. The CFR counterpart to `chapter`: pass a hit's `parent.part` back. Pair with `titleNumber`; an unpaired part is rejected. | |
| limit | No | Number of results to return per page. | |
| query | Yes | Search query in natural language. | |
| state | No | Jurisdiction. A 2-letter code for one of the 52 supported US jurisdictions (50 states + DC + PR), or `federal` for USC / CFR / Constitution / federal rules. Pass a list to search several at once. Case-insensitive. Omit to search every jurisdiction. | |
| agency | No | Federal Register agency slug, e.g. `environmental-protection-agency`. Pass a list to match any of several. Applies to `FEDERAL_REGISTER` and `EXECUTIVE_ACTION`; other corpora carry no agency, so combining this with them returns nothing. | |
| fields | No | Return only these result fields, e.g. `["title", "excerpt"]`. A result carries 40+ fields, most null on any given row. `actId` and `citation` are always included. Unknown names are rejected 422. Omit for the full object. | |
| offset | No | How many results to skip, for paging. Every page of a query is cut from one ranking, so results never repeat or go missing between pages. The deepest reachable result is `offset` + `limit`; check `hasMore`. | |
| source | No | The named body of law within a `corpusType` that folds several together: `FEDERAL_RULES` into `frcp`/`fre`/`sct`, `CFR` into `far`/`dfars`, `AGENCY_GUIDANCE` into ~34 agency sources. Every result carries its own `source`, so a hit's value can be passed straight back. | |
| yearTo | No | Only sections last amended in or before this year. This filters the LAST amendment, so a section amended in 2025 is excluded by `yearTo=2024` even though it existed in 2024. A currency filter, not point-in-time retrieval. | |
| chapter | No | One or more chapters within a title or code, e.g. `21` for USC Title 42 Chapter 21. Pass a hit's `parent.chapter` back to search its neighbors. Chapter numbers repeat across titles, so pair with `titleNumber` (USC) or `code` (state); an unpaired chapter is rejected. | |
| yearFrom | No | Only sections last amended in or after this year; pair with `yearTo` for a window. Tracks the publisher's own amendment credit, not when we rebuilt the corpus. About a fifth of sections carry no credit and are excluded once either bound is set. | |
| actStatus | No | Positively scope to raw publisher statuses: `repealed` for dead law only, `in_force` for sections affirmatively marked current. The inverse of `excludeRepealed`, and what a compliance diff asking what was LOST needs. Combining a dead status with `excludeRepealed: true` is rejected 422. | |
| matchType | No | `any` (default) is hybrid semantic + keyword ranking, for natural-language questions. `all` requires every query term; `phrase` matches an exact phrase, for a defined term. To pull up one section, pass its citation as the query and it resolves to that section at rank 1. | any |
| corpusType | No | Restrict to one corpus, or several as a list. Federal: `USC`, `CFR`, `CONSTITUTION`, `FEDERAL_RULES`, `FEDERAL_REGISTER`, `EXECUTIVE_ACTION`, `SENTENCING_GUIDELINES`, `US_TAX_TREATY`, `SESSION_LAW` (Statutes at Large, as enacted). Pair with `state`: `STATE`, `REGULATION`, `STATE_RULES`, `STATE_CONSTITUTION`, `STATE_AGENCY_GUIDANCE`. Omit for all. | |
| includeBody | No | Return the full text of every hit inline, on each result's `body`, instead of making you fetch it per section afterwards. **Why it exists.** Search returns a ranking preview, so the documented flow was search then one `/section/{actId}/body` call per hit. Measured 2026-09-02 that is about 2s for the search plus about 3s for each body, so a page of five sections cost six round trips to put real law on screen. This collapses it to one. **Cost**: the 4-credit search PLUS the ordinary 6-credit body price for each row that actually returns text. Ten rows with text is 4 + 60 = 64 credits. A row whose text cannot be resolved comes back with `body: null` and is NOT charged, so read `creditsConsumed` rather than computing it from `limit` -- it is the same price as fetching them yourself, so this buys latency, not a discount. ⚠️ It multiplies with `limit`. `limit: 50` with this set is 304 credits in a single call. Page deliberately. Prefer this over raising `excerptChars`: the excerpt is windowed around the match and can begin mid-section, dropping a leading subsection marker, so it is not safe to quote. `body` is the publisher's text. | |
| publishedTo | No | Only return Federal Register documents published on or before this date. | |
| titleNumber | No | Filter by USC/CFR title number (e.g., 17 for SEC, 42 for civil rights). Only meaningful for `USC`/`CFR`; ignored for state corpora whose titles are alphabetic (e.g. Texas `pe` = Penal Code). | |
| changedSince | No | Only sections we OBSERVED changing on or after this date (`YYYY-MM-DD`). Observed, not effective: the date we saw it, an upper bound on when it took effect. Capture began long after the corpus did and events sweep at 24 months, so empty means no captured change, never that nothing was amended. | |
| documentType | No | Federal Register document stage: `final` (a rule in force), `proposed` (an NPRM), or `presidential` (a Presidential Document, the `EXECUTIVE_ACTION` corpus). Previously visible only as an `actId` prefix (`FR_RULE_` vs `FR_PRORULE_`) with no way to filter. | |
| excerptChars | No | Characters of matching text to include in each result's `excerpt`. The excerpt is a ranking preview; use `/us/statutes/section/{actId}/body` for the full text. Default 500. | |
| publishedFrom | No | Only return Federal Register documents published on or after this date (`YYYY-MM-DD`). This is the PUBLICATION date, which is not the same as `yearFrom`: that filters the version year of a section. | |
| excludeRepealed | No | Drop sections whose own status says they are not operative (repealed, renumbered, transferred, expired, superseded, omitted, and the rest). Removes what we KNOW is dead; it does not promise the remainder is good law. Read `goodLawStatus` per result to tell them apart: `good_law` is checked, `unknown` is unchecked. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||