@pipeworx/tw-law

Taiwan's national statutes and the Constitution — full text in Chinese, plus the Ministry of Justice's own official English translation where one exists — searchable by title, resolvable by exact citation, and readable one provision at a time.

Part of Pipeworx — an MCP gateway connecting AI agents to 1857+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• tw_law_search(query, limit?) — find a law by title keyword, Chinese or English ("個人資料保護法", "Personal Data Protection", "民法").

• tw_law_info(pcode?, name?) — a law's full metadata: level, category, official English title if any, repeal status, the last amendment date and the date that amendment takes/took legal effect as SEPARATE fields, and the promulgation history (Chinese, and English when translated).

• tw_law_toc(pcode?, name?, offset?, limit?) — a law's chapter/section structure and article numbers, paged.

• tw_law_article(pcode?, name?, article) — one article's full text, Chinese plus the official English translation when the Ministry has published one, labelled official.

Related MCP server: mcp-taiwan-legal-db

Auth

Keyless.

Data sources

• Taiwan Ministry of Justice, Laws & Regulations Database (全國法規資料庫) — the Chinese text of every national statute and the Constitution, plus the Ministry's own official English translations for the subset it has translated (973 of 1,351 laws as of the 2026-10-15 load).

The source publishes its whole catalog only as two bulk exports (Chinese, English), never a per-law or per-article live route — confirmed 2026-10-15. Per Bruce's 2026-09-23 local-copy ruling, this pack reads from a D1 copy loaded by scripts/tw-law/load-data.mjs, refreshed by re-running that script. data_as_of on every response is when that load last ran.

Licence: 政府資料開放授權條款-第1版 (Government Open Data Licence v1), the licence the source's own data-reuse declaration (law.moj.gov.tw/Service/Copyright.aspx) names — free, non-exclusive, re-licensable, and explicitly permits reproduction, adaptation and public transmission (a mirror, not only a live proxy), conditioned on citing the source. Every response carries source.

English translations are tied to the exact Chinese version

Chinese and English are two separate bulk exports from the same publisher, joined by this pack's loader at load time, by law title and then by article number (normalizing "第 6-1 條" / "Article 6-1" / "6-1" to the same key) — never machine-translated, never guessed. An article with no official translation returns eng_content: null and has_official_english_translation: false rather than a translation that doesn't exist. A law can gain or lose an official translation between loads; tw_law_info/tw_law_search report has_official_english_translation as of the current data_as_of.

Notes

• tw_law_search is a TITLE search — it will not find a law by a phrase that appears only inside an article's text.

• Article numbering is not always contiguous: amendments can delete an article or insert a sub-article ("第 1-1 條" after "第 1 條"). Use tw_law_toc to see a law's real article numbers rather than assuming 1..N.

• effective_date and last_amended_date are tracked separately because Taiwanese statutes are routinely amended on one date and brought into force on another (sometimes "date to be set later by the Executive Yuan" — surfaced as effective_date_pending: true, with the full effective_note explaining which provisions are affected).

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/tw-law/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 1857+ 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/tw_law_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"個人資料保護法"}'

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

Run it from npm

@pipeworx/mcp-tw-law 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/tw-law/mcp endpoint shown above. It needs network access; there is no offline mode.

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

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 Tw Law data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT