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

• nl_wetten_search(query, as_of?, limit?) — title search over Dutch 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.
• nl_wetten_get_law(bwb_id, as_of?, offset?, limit?) — one regulation's 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 — has_more/next_offset).
• nl_wetten_get_article(bwb_id, article, as_of?) — one article's original 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.

Every date returned is a separate field: as_of (what you asked for), toestand_valid_from / toestand_valid_until (how long the resolved consolidated version has applied), and — on nl_wetten_get_article — article_in_force_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

• KOOP (the Dutch government's publications agency), Basiswettenbestand (BWB) — the consolidated register of Dutch national legislation, covering every statute, AMvB, ministerial regulation and treaty KOOP publishes.

Notes

• The upstream 406s without an explicit Accept: application/xml header. 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.
• A title search without a validity-date filter returns one record per 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.
• Article full text has no JSON form. The consolidated text is only 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 numbers follow the source's own numbering, which is not always plain integers — e.g. "1:3" (chapter:article) or "3:9a" (a lettered insertion). Use the exact string nl_wetten_get_law lists.

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 — 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 1815+ 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/nl_wetten_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"Algemene wet bestuursrecht"}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-nl-wetten

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Nl Wetten data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT