Kentucky Code MCP server

@pipeworx/kentucky-code

Kentucky Revised Statutes (KRS) — state statutes by citation and by topic search, with legislative/amendment history. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1743+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

("507.020", "KRS 383.580", "§ 507.020"). Returns the catchline, the full statutory text, the effectivedate, and the history line (the Acts that enacted and amended it). A prior (pre-amendment) version's text is not available anywhere online — historicalversions says so rather than silently omitting it.

• ky_statute(citation) — the current text of a KRS section by citation

body text, not just catchlines ("landlord" surfaces KRS 383.580 "Security deposits", a catchline that contains neither word). Returns matching citations and catchlines; pass a citation to ky_statute for the full text.

• ky_search(query, limit?) — full-text topic search over the statutory

Auth

Keyless. No signup, no key, on either side of the call.

Data sources

Legislative Research Commission's own citation/topic search, GET with searchPhrase, statuteRange=true&startRange=1&endRange=999, and searchStatuteNumber=true for an exact-citation lookup. Needs a fresh RequestVerificationToken header, read from an inline on — NOT cookie-bound (confirmed: the search page sets no cookie), so one GET for the token followed by one GET against the API, per call, is the whole mechanism. No login.

• — the

matched section's full text, served as a per-section PDF (content-disposition: inline;FileName="KRS507_020(K).pdf"). There is no HTML page with the statutory text anywhere on the site; the chapter index pages list only catchlines. Extracted via the new extractPdfText helper in shared/src/pdf-text.ts (see that file for what it does and does not handle) — this repo had no PDF text extraction before this pack.

• — the

The opaque-id trap, and why this isn't the two-hop resolver. The August state-law survey (docs/state-law-probe.md) flagged Kentucky's statute URLs as addressed by an opaque database id with no derivable mapping from the citation — the same shape Vermont and Connecticut solved with a two-hop fetch through the chapter index. Kentucky's chapter index pages (chapter.aspx?id=) DO carry that mapping (confirmed: Chapter 507's index lists ".020 Murder." next to its id), so the two-hop route would work — but a simpler ONE-hop route also works and is what this pack uses: the LRC's own search API resolves a citation straight to its id, because it is a real full-text search over the whole KRS rather than a title/catchline index (verified live: searching "landlord" surfaces KRS 383.580, whose catchline is just "Security deposits.").

Four capabilities, three available. Citation lookup and topic search are both the same search endpoint with a flag; amendments/history is the statute's own History: line, parsed out of the extracted PDF text. The fourth — the TEXT of a section as it read before a given amendment — is not published online anywhere: a superseded id redirects to an "Invalid Statute" page instructing the reader to e-mail the Reviser of Statutes for it. This pack reports that as historical_versions, not as a silent gap.

Division/chapter-heading rows. The search API's Type field is "K" for a real statute section, "D" for a chapter/division heading (no statutory text — kystatute reports notasection rather than fetching a PDF for it), and "R" for a repealed section (text still returned; typelabel says which).

Quick Start

Shortened. The full README is on GitHub.