Searches EU legal acts by title substring (contiguous phrase, case-insensitive — not tokenized full-text search). For topic-based discovery use eurlex_by_eurovoc instead. Broad single-word terms can be slow; narrow with resource_type or date_from/date_to. Supports all 24 official EU languages (pass the Cellar 3-letter code, e.g. DEU, ENG, FRA, POL, SPA); match the query term to the chosen language. Results are newest-first within the fetched sample, not necessarily the globally newest match for very broad queries.

Fetches the full text of an EU legal act. Identify it by celex_id (e.g. "32024R1689"), by eli (e.g. "reg/2016/679" or a full ELI URL), or by oj_ref (post-2023 Official Journal reference, e.g. "OJ:L_202401689") — provide exactly one. Paginate long documents with offset and max_chars: pass the previous response's next_offset to continue reading until it is null.

Fetches metadata for an EU legal act: document/entry-into-force/end-of-validity dates, in-force status, authors, legal basis (CELEX IDs of the acts it is based on), EuroVoc descriptors, and directory codes. Identify the act by celex_id (e.g. "32024R1689"), by eli (e.g. "reg/2016/679" or a full ELI URL), or by oj_ref (post-2023 Official Journal reference, e.g. "OJ:L_202401689") — provide exactly one.

Finds citation relationships for an EU legal act: cites, cited_by, amends/amended_by, based_on/basis_for, repeals/repealed_by. direction="both" runs a balanced split so recent cited_by entries cannot crowd out cites results; the response's counts field reports how many of each side were found. The limit is divided evenly between the two directions and is not back-filled from the richer side, so direction="both" can return fewer than limit total results even when one side has more matches available.

Searches EU legal acts by EuroVoc thematic concept — the right tool for "documents about X" when the term may not appear in the title. Accepts a concept label in any official EU language (e.g. "artificial intelligence") or a EuroVoc URI; label resolution automatically falls back across all 24 official EU languages if the request language has no match, so the example works regardless of the default language.

Fetches the latest consolidated (currently in-force) version of an EU legal act via ELI, with all amendments merged in. Identify the act with celex_id (e.g. "32016R0679") OR with doc_type + year + number — provide exactly one of the two. celex_id must be a sector-3 secondary-law CELEX (3YYYY[R|L|D]NNNN).

Finds Court of Justice of the EU (CJEU) case law — judgments (JUDG), orders (ORDER), and Advocate General opinions (OPIN_AG) of the Court of Justice and the General Court. Look up rulings four ways (at least one required, combinable): query=title/party substring (e.g. "Schrems"), celex_id=a sector-6 CELEX (e.g. "62012CJ0131"), ecli=a European Case Law Identifier (e.g. "ECLI:EU:C:2014:317"), or related_celex=a legal act's CELEX (e.g. "32016R0679") to get the case law interpreting that act. Narrow with court (COURT_JUSTICE/GENERAL_COURT), type, language, and date_from/date_to. Unlike eurlex_search (which searches legislation by title), this tool is scoped to case law and understands ECLIs and act-to-case-law relations. Each hit returns celex, ecli, title, date, type, and eurlex_url.

Lists the national implementing measures (NIMs) EU member states enacted to transpose a given EU directive into national law — the answer to "how did member state X implement directive Y" for transposition and compliance tracking. Input celex_id is the directive's sector-3 CELEX (e.g. "32022L2555" for NIS2, "31995L0046" for the Data Protection Directive); optionally filter by country (2-letter member-state code, e.g. "DE"). Each result gives the member state, the national measure's title (in that state's own official language — not translated), its date, the sector-7 NIM CELEX reference, and a EUR-Lex URL. total_found reports the full count; results is capped at limit. For the directive itself use eurlex_fetch/eurlex_metadata; regulations and decisions have no NIMs.

Returns the outline (table of contents) of an EU legal act — its chapters, sections, articles and annexes — each with a character offset into the document's plain text. Use it as a map for targeted reading: read an article's offset from the outline, then call eurlex_fetch(celex_id, format:"plain", offset, max_chars) with that offset to jump straight to that article instead of paging from the top of a long act. Identify the act by celex_id (e.g. "32024R1689"), eli, or oj_ref — provide exactly one. Each outline entry has: level (1=part/title/annex, 2=chapter, 3=section, 4=article), label (e.g. "Article 5", "CHAPTER III"), title (the heading's subtitle, e.g. "Prohibited AI practices"), and offset. total_headings is the full count; the returned list is capped at 300 for very large acts (truncated=true). Heading offsets are specific to the chosen language and to plain (tag-stripped) text — pass the SAME language to the follow-up eurlex_fetch call and keep format:"plain". Heading recognition covers English, German and French documents. For case-law documents (CELEX sector 6, e.g. CJEU judgments) the outline additionally lists each numbered judgment paragraph as "Paragraph N" (level 4); numbered-paragraph detection works in any language (it keys on the paragraph number, not heading words) — so you can get the offset of, say, paragraph 72 of a judgment and jump eurlex_fetch straight to it.

Returns the EU's official plain-language summary (LEGISSUM) of a legal act — a short editorial overview written for non-lawyers ("what is the aim", "key points", "from when does it apply"), NOT the binding legal text. Input is the act's celex_id (e.g. "32016R0679" for the GDPR, "32022R2065" for the Digital Services Act) and a language (any of the 24 official EU languages; summaries are usually available in all of them). Output is the summary text (plain, HTML stripped) plus its LEGISSUM id, title, last-update date, an obsolete flag, and source_url (the EUR-Lex summary page). Long summaries paginate via max_chars/offset exactly like eurlex_fetch — pass the previous response's next_offset to continue. Several thousand major acts have a summary; many acts have none (you get a clear "no summary" message). When an act has several summaries the most current non-obsolete one is returned and the rest are listed in other_summaries. For the full legal text use eurlex_fetch; for structured metadata use eurlex_metadata.

Expert escape hatch: run a raw, read-only SPARQL 1.1 query directly against the EU Publications Office (Cellar) endpoint when the higher-level tools (eurlex_search, eurlex_metadata, eurlex_citations, eurlex_case_law, eurlex_transposition, eurlex_summary, …) cannot express what you need. Requires knowledge of the CDM ontology — READ THE eurlex_guide PROMPT FIRST for the property cheat sheet (celex, title, language, dates, citations, case law, transposition, summaries). Only SELECT and ASK are allowed; SPARQL Update (INSERT/DELETE/…) and federated SERVICE clauses are rejected before the query is sent. A SELECT with no top-level LIMIT gets LIMIT 50 appended (set limit_added); a top-level LIMIT above 100 is rejected. The response mirrors SPARQL JSON — vars + bindings for SELECT, boolean for ASK — plus row_count and a truncated flag (whole rows are dropped past ~40k characters). CELEX/ELI literals are typed xsd:string, so match them with FILTER(STR(?x) = "..."). Example: PREFIX cdm: http://publications.europa.eu/ontology/cdm# SELECT ?celex WHERE { ?w cdm:resource_legal_id_celex ?celex . FILTER(STR(?celex) = "32016R0679") } LIMIT 1