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 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• gesetze_search(query, limit?) — find a law by title keyword or abbreviation ("BGB", "Datenschutz"). An abbreviation match returns that one law directly; otherwise ranks law titles by word overlap.
• gesetze_law_info(law) — amendment metadata ("Stand") for one law: 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.
• gesetze_structure(law, section_id?, depth?, provision_limit?) — the law's table of contents (Buch/Abschnitt/Titel/Kapitel) with its §/Art. provisions listed under each heading. Paged: a branch with more provisions than provision_limit reports has_more_provisions rather than truncating silently.
• gesetze_provision(law, provision) — full text of one § (Paragraph) or 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.

Auth

Keyless.

Data sources

• Bundesministerium der Justiz (BMJ) / juris GmbH, Gesetze im Internet — the federal government's official collection of German statutes and ordinances currently in force, each as structured XML with its own amendment metadata.

Notes

• Abbreviation matching. The collection's own table of contents carries 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 gesetze_search/gesetze_law_info/ gesetze_structure/gesetze_provision 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 gesetze_search's title search is the way in.
• Per-law fetch is live, per call. Only the catalog (title + law 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 gesetze_law_info/gesetze_structure/gesetze_provision — 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.
• § vs. Art. Most laws number their provisions "§ N"; a handful (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.
• Granularity. A provision is one § or Art. (the source's own unit). 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.
• Copyright. German federal legislative and administrative texts are "amtliche Werke" and are not protected by copyright (§ 5 Urheberrechtsgesetz).
• Index refresh. scripts/bake-de-gesetze-index.mjs regenerates 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.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "de-gesetze": {
      "url": "https://gateway.pipeworx.io/de-gesetze/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/de-gesetze/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1863+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/gesetze_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"Datenschutz"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/gesetze_search. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-de-gesetze is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/de-gesetze/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "de-gesetze": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-de-gesetze"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about De Gesetze data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT