io.github.matematicsolutions/il-eli-mcp

Full-text search over Israeli law names (Hebrew). Args: query: free text in Hebrew, e.g. a keyword from the law's title. limit: max results (default 20). Returns: ``{"total": int, "items": [...]}`` - each item carries the citation contract.

Fetch full detail for one Israeli law by its IsraelLawID. Args: israel_law_id: the Knesset OData IsraelLawID (from `il_search_laws`). Returns: A dict with ``name``, ``knesset_num``, ``is_basic_law``, ``publication_date``, ``latest_publication_date``, ``law_validity_desc``, ``lex_uri``, ``human_readable_citation``, ``source_url``.

Search published Israeli law versions (KNS_Law), including consolidated texts. Complements `il_search_laws`: that tool covers the KNS_IsraelLaw registry (validity status, Basic Law flag), this one covers KNS_Law - the published versions whose official PDF documents are reachable via `il_get_law_documents`. The two id spaces are disjoint. Args: query: free text in Hebrew, matched against the published version's name. limit: max results (default 20). Returns: ``{"total": int, "items": [...]}`` - each item carries ``law_id``, version metadata (type, sub-type such as a consolidated text, publication series) and the citation contract.

Official document files (PDFs) for one published law version. Args: law_id: the KNS_Law id from `il_search_law_texts` (NOT `israel_law_id`). Returns: A dict with the published law's metadata + citation contract and ``documents``: a list of official files, each with ``file_path`` (a fs.knesset.gov.il PDF URL - the operative text; fetch it client-side), ``group_type_desc`` and ``application_desc``.

Keyword search over a local, pre-downloaded corpus of Israeli court judgments. NOT a live API call. The corpus (10,558 Hebrew judgments from Family, District, Magistrate, Labor, Military and Administrative courts) is a static HuggingFace dataset (`guychuk/case-law-israel`) downloaded once and cached locally on first use of this tool - later calls only touch the local cache. Its license is undocumented; treat results as for analysis, not for redistribution. Args: query: free text in Hebrew, matched against title/full text/judges/case number. court: optional substring filter on the court type label (Hebrew), e.g. a fragment of "בית משפט השלום" (Magistrate) or "בית דין לעבודה" (Labor). limit: max results (default 20). Returns: ``{"total": int, "items": [...], "license_status": str}`` - each item carries the citation contract plus the judgment fields (including the full ``document_text``).

Declare what this connector covers, how it is sourced, and what it does NOT cover. Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty: the absence may be a gap in this connector rather than in the law. Every gap carries a fallback saying where to look instead. Returns: ``Coverage`` with families, an as-of note, and a non-empty list of known gaps.

Fetch full detail (including full judgment text) for one case by its judgment_id. Reads from the same locally-cached dataset as `il_search_case_law` - see that tool's docstring for the download/caching/license notes. Args: judgment_id: the dataset's ``judgment_id`` (from `il_search_case_law` results). Returns: A dict with the judgment's fields (title, court, district, judges, full ``document_text``, etc.), ``human_readable_citation``, ``source_url``, and ``license_status``.