Boe Legislacion MCP server

@pipeworx/boe-legislacion

Spain's consolidated legislation — every Spanish statute and royal decree kept up to date with every amendment folded in, plus the daily table of contents of the state gazette, from the Agencia Estatal Boletín Oficial del Estado (BOE).

Part of Pipeworx — an MCP gateway connecting AI agents to 1800+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

legislation by words in the title (e.g. "Código Civil", "ley de propiedad horizontal"). Returns matching laws with their BOE id, legal rank, issuing department, scope (national/regional), key dates, and the official BOE page URL for each. Pass the returned id to boe_law.

• boesearchlaw(query, ambito?, limit?, offset?) — search consolidated

article: metadata (rank, department, consolidation status, dates), subject tags, notes, and a table of contents of its articles/sections ("bloques") — capped at 200 entries and marked truncated for large codes. With article (a block id from that table of contents, e.g. "a1" for Artículo 1): the actual text of that one article across every historical version it has had, each dated, with the current one flagged.

• boe_law(id, article?) — one consolidated law by its BOE id. Without

disposition and announcement published that day, grouped by section and issuing department, with each item's BOE id and title. BOE does not publish every day (no Sunday issue, some holidays); those dates come back found: false, never an empty list.

• boedailysummary(date) — table of contents of one day's BOE issue: every

Auth

Keyless. The upstream open-data API requires no registration, key, or click-through terms — it is served to anyone with Accept: application/json.

Data sources

the consolidated-text database of Spanish state and regional legislation, kept current with every amendment.

• Agencia Estatal Boletín Oficial del Estado (BOE), Legislación Consolidada —

of contents of the state gazette.

• Agencia Estatal Boletín Oficial del Estado (BOE), Sumario — the daily table

Notes

the upstream ignores Accept: application/json entirely and always answers a fixed small XML envelope (status code + text, empty data) regardless of what was requested. Every call here reads the body as text first and only parses it as JSON when it looks like JSON, so an error message is never lost to a failed res.json().

• The Accept header is honoured on 200 only. On any error (400/404/500)

with "data": "" — an empty string, not [] or {} — while a populated list and a single-record lookup are both array-wrapped ("data": [...], even for exactly one record). boesearchlaw and boe_law normalise this and report found: false with plain wording on a genuine miss, never an empty array dressed as success.

• The empty-result shape is not uniform. A zero-match search answers 200

contents (texto/indice) is available as JSON; the actual block text is XML-only. There is no XML parser in the Workers runtime, so boe_law with article extracts paragraphs with targeted regex over BOE's fixed one-block, one-or-more-versions, paragraph-per-version XML shape — reliable for real statute text, not a general-purpose XML parser.

• Article/section text has no JSON form at all. Only the table of

2,444 blocks. boe_law without article caps what it inlines and reports articles.total / articles.truncated rather than ever returning the whole thing — use article to read one block at a time.

• Large codes are enormous. The Código Civil's table of contents alone is

offset paginate, and shown tells you how many came back this call.

• The upstream does not report a total match count for search — limit /

Quick Start

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

Shortened. The full README is on GitHub.