io.github.cyanheads/eur-lex-mcp-server

Search the EuroVoc thesaurus, resolving a keyword into concept URIs usable in the eurovoc_concept subject filter of eurlex_search_documents. CELLAR indexes no judgment, order, or Advocate General opinion of the Court of Justice or General Court by EuroVoc concept; only EFTA Court judgments carry one, so search case law by subject with eurlex_get_cases subject. Matches both preferred and alternative (non-preferred) labels, so a common synonym reaches the concept it stands for. Returns each concept URI, its preferred label in the requested language, code, broader (parent) label, and the alternative label that matched when one did. Concepts with an exact label match come first, then those whose label or one of its words starts with the keyword, then other substring matches, each group ordered by preferred label.

Search CJEU and General Court case law — judgments, orders, and Advocate General opinions and views — by case number, court, case type, member state, procedure type and outcome, subject, keyword, and date range. A case number reaches every judgment, order, AG opinion, and AG view filed under it. By default only these primary records are returned; derivative judicial information notices, case abstracts, summaries, and corrigenda are excluded so distinct cases fill the page (set include_derivative to include them). Keyword matches English case titles (which carry party names) and CELEX strings; there is no full-text body search. member_state, procedure_type, outcome, and subject match the facts CELLAR records on each case, so a case it records none of a filtered fact for never matches. Returns each case with its CELEX number (whose sixth character names the court: C, T, or F), work URI, ECLI, date, and type; where CELLAR records them, its countries, procedure types with outcome, subjects, and procedure languages; and — parsed from the title where present — the formation, Advocate General, parties, referring court, subject matter, and case reference. The raw CELLAR title is returned only when those fields do not capture all of it.

Fetch the metadata and full text of an EU act or case-law record by CELEX number, ELI URI, or work URI. Returns structured metadata (title, date, type, ELI, Official Journal reference, typed dates of effect, transposition deadlines, author institution, Advocates General, legal basis, EuroVoc subjects, in-force status and, for an act not in force, its repealing acts, end of validity, or pending entry into force; the legislative procedures the act belongs to, each with its status — adopted, withdrawn, pending, or not adopted — and the acts it produced; for case law, the ECLI, the formation, referring court, subject matter, and case reference parsed from the title, and the countries, procedure types with their outcome, subjects, and procedure languages CELLAR records) plus the body as HTML, Markdown, or Formex4 XML, defaulting to English with automatic fallback. Every body returned in one call is capped at 100,000 characters — paged and full windows page onward with offset/limit; use outline: true for a heading map and select to pull specific articles, chapters, recitals, or annexes of an act, or the headed sections and operative part of a judgment or order, reading a selected section on its own from the offset and chars in selected_sections.

Traverse the one-hop CDM relationship graph of an EU act: what it amends or is amended by, what it repeals or is repealed by (explicit and implicit), its consolidated versions, national transposition measures (on a first page also counted per member state, naming the member states with none), its legal basis and the works adopted under it, the proposal it adopts (or, for a proposal, the act that adopted it), the CJEU rulings interpreting it (or, for a ruling, the acts it interprets), and works that cite it. Amendment, repeal, interpretation, and adoption rows carry the provisions CELLAR records each edge as targeting, article narrows interpreted_by to the rulings on one article, and related_sectors keeps only the related works of the named CELEX sectors (3 legal acts, 5 preparatory acts, 6 case law, …). Returns direct relations only, paginated per relation type and direction. Requires a CELEX number or CELLAR work URI.

Resolve an EU legal citation — a CELEX number, ELI URI, ECLI, an OJ citation naming its act type and year (e.g. "Regulation (EU) 2016/679", "Directive 95/46/EC"), an Official Journal reference naming its issue, date, and first page (e.g. "OJ L 119, 4.5.2016, p. 1"), a Commission document number (e.g. "COM(2021) 206 final", also SEC, SWD, JOIN), or an interinstitutional procedure reference (e.g. "2021/0106(COD)", resolved to the act that initiated it) — to its canonical CELLAR work, confirming it exists before you fetch or traverse it. Returns the work URI, confirmed CELEX number, document type, date, and the ECLI of a case that carries one. A CELEX that CELLAR holds under several works resolves to the one the EUR-Lex content resolver serves. An ECLI shared by several records (a judgment and its abstract or extract, or a joined AG opinion) resolves to the primary record with the lowest CELEX. An OJ reference whose first page starts several acts, a document number CELLAR holds in several parts, and a procedure with several initiating acts return found false, the notice naming each CELEX; a procedure with no initiating act returns found false, the notice naming the CELEX of each act it produced.

Run a raw, read-only SPARQL SELECT against the CELLAR Virtuoso endpoint — an escape hatch for CDM ontology traversals the curated tools do not cover. Only SELECT is accepted; update forms and ASK/CONSTRUCT/DESCRIBE are rejected before execution, and results are capped at the server row cap (100 by default). The cdm:, skos:, and xsd: prefixes are auto-injected.

Search EU legislation, treaties, and preparatory acts across the CELLAR corpus by document type, date range, EuroVoc subject, author institution, and in-force status. Keyword matches English titles and CELEX strings only — there is no full-text body search. Corrigenda are excluded by default so primary acts fill the page (set include_corrigenda to include them). Returns a page of CELEX numbers, work URIs, type labels, dates, and titles, newest first, each flagged with is_consolidated and is_corrigendum. At least one filter is required.