Nl Wetten MCP server

@pipeworx/nl-wetten

Dutch national legislation, consolidated and point-in-time: search by title, look up a regulation's structure by its BWB id, and read one article's original Dutch text as it stood on any date.

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

national legislation; returns the regulation(s) matching, each resolved to the version in force on as_of (default today), with its BWB id (BWBR...). Title search only, not full-text search.

• nlwettensearch(query, as_of?, limit?) — title search over Dutch

citeertitel, authority, legal domain(s), the resolved version's own validity period, its chapter structure, and a paged list of article numbers (never truncated silently — hasmore/nextoffset).

• nlwettengetlaw(bwbid, as_of?, offset?, limit?) — one regulation's

Dutch text, broken into its numbered "lid" (paragraph) subdivisions, plus the date that exact text took effect and the resolved version's validity period. Pass an earlier as_of to read a past version of the same article.

• nlwettengetarticle(bwbid, article, as_of?) — one article's original

Every date returned is a separate field: asof (what you asked for), toestandvalidfrom / toestandvaliduntil (how long the resolved consolidated version has applied), and — on nlwettengetarticle — articleinforce_since (when that article's own text last changed), which can differ from the toestand's own start date when the article itself hasn't been amended since an earlier date.

Auth

Keyless.

Data sources

— the consolidated register of Dutch national legislation, covering every statute, AMvB, ministerial regulation and treaty KOOP publishes.

• KOOP (the Dutch government's publications agency), Basiswettenbestand (BWB)

Notes

No Accept header at all (what a bare fetch() sends) and Accept: application/json both get HTTP 406, even for an otherwise well-formed, healthy query. Every request this pack makes sets the header.

• The upstream 406s without an explicit Accept: application/xml header.

historical version, not per law** — "Algemene wet bestuursrecht" alone comes back 40+ times across its amendment history. Every search here adds the as-of date so each regulation resolves to exactly one version.

• **A title search without a validity-date filter returns one record per

published as XML, and a single law's document can run several MB (the Algemene wet bestuursrecht's current version is ~2.6 MB). There's no XML parser in the Workers runtime, so article text is extracted with targeted pattern matching over the register's fixed element structure — correct for real statute text, not a general-purpose XML parser.

• Article full text has no JSON form. The consolidated text is only

plain integers — e.g. "1:3" (chapter:article) or "3:9a" (a lettered insertion). Use the exact string nlwettenget_law lists.

• Article numbers follow the source's own numbering, which is not always

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/nl-wetten/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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.

Shortened. The full README is on GitHub.