De Gesetze MCP server

@pipeworx/de-gesetze

German federal statutes and ordinances (Bundesrecht) — search by title or official abbreviation, read a single § or Art. in full, browse a law's structure, and get its amendment status ("Stand").

Part of Pipeworx — an MCP gateway connecting AI agents to 1815+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

abbreviation ("BGB", "Datenschutz"). An abbreviation match returns that one law directly; otherwise ranks law titles by word overlap.

• gesetze_search(query, limit?) — find a law by title keyword or

official abbreviation/title, date of promulgation, official publication citation, the amendment-status entries (Neufassung/Stand), and the entry-into-force date when the source publishes one.

• gesetzelawinfo(law) — amendment metadata ("Stand") for one law:

law's table of contents (Buch/Abschnitt/Titel/Kapitel) with its §/Art. provisions listed under each heading. Paged: a branch with more provisions than provisionlimit reports hasmore_provisions rather than truncating silently.

• gesetzestructure(law, sectionid?, depth?, provision_limit?) — the

Art. (Artikel), by abbreviation and number ("823", "§ 823", "823a", "Art 1"), with its title and its own amendment/application footnote when the source attaches one.

• gesetze_provision(law, provision) — full text of one § (Paragraph) or

Auth

Keyless.

Data sources

the federal government's official collection of German statutes and ordinances currently in force, each as structured XML with its own amendment metadata.

• Bundesministerium der Justiz (BMJ) / juris GmbH, Gesetze im Internet —

Notes

no separate abbreviation field — only a title and a per-law identifier. For the large majority of entries that identifier IS the law's lowercase official abbreviation (the publisher's own convention: bgb -> BGB, stgb -> StGB, estg -> EStG), and gesetzesearch/gesetzelawinfo/ gesetzestructure/gesetzeprovision all resolve on that basis first. This is a documented convention, not a guarantee for every one of the ~6,100 entries — an obscure ordinance's identifier occasionally departs from its cited abbreviation, in which case gesetzesearch's title search is the way in.

• Abbreviation matching. The collection's own table of contents carries

identifier, ~6,100 entries) is baked into a lookup index; a law's full text, structure and amendment metadata are fetched and parsed live on each call to gesetzelawinfo/gesetzestructure/gesetzeprovision — proxied, never mirrored. A short per-isolate cache avoids re-fetching the same law repeatedly in a burst of calls; it is not a persistent copy.

• Per-law fetch is live, per call. Only the catalog (title + law

(constitutional and some international-treaty texts, e.g. the Grundgesetz) use "Art N" instead. gesetze_provision matches on the bare number/letter token, so either symbol works regardless of which one a given law actually uses — you do not need to know in advance.

• § vs. Art. Most laws number their provisions "§ N"; a handful

Absätze (paragraphs) and Sätze (sentences) within a provision are part of its text, not separately addressable — consistent with how the publisher itself structures the document.

• Granularity. A provision is one § or Art. (the source's own unit).

"amtliche Werke" and are not protected by copyright (§ 5 Urheberrechtsgesetz).

• Copyright. German federal legislative and administrative texts are

src/de-index-data.ts from one live call to the publisher's table of contents; it is registered in workers/gateway/src/pack-baked-indexes.json so it ships to KV, never into the gateway bundle.

• Index refresh. scripts/bake-de-gesetze-index.mjs regenerates

Quick Start

Shortened. The full README is on GitHub.