Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "get_article", "get_law_texts" and "search_legislation"
When calculated_current is present, use its text_ar for current monetary amounts and cite its authority.url. Identify this as calculated under the authority, never as verbatim published wording. The article text_ar and source fields remain published wording. Get one article's verbatim Arabic text as in ⟨140 unchanged words⟩
When calculated_current is present, use its text_ar for current monetary amounts and cite its authority.url. Identify this as calculated under the authority, never as verbatim published wording. The article text_ar and source fields remain published wording. Get the verbatim texts of a law's articles ⟨55 unchanged words⟩
When calculated_current is present, use its text_ar for current monetary amounts and cite its authority.url. Identify this as calculated under the authority, never as verbatim published wording. The article text_ar and source fields remain published wording. Search Lebanese legislation (laws, decrees, decisions), ⟨201 unchanged words⟩
Changed the definition of "get_ruling"
⟨14 unchanged words⟩ text when the Centre holds it as typedtext (sometext.rulingsWhenexistavailable,onlypagesasreturnsathe scannedfile).judgment's machine reading, with low_confidence: true on hard-to-read pages where errors are expected. pdf_url is the full judgment's scan on the ⟨24 unchanged words⟩
Added "list_gazette_issues" and "list_legislation"; changed the definition of "get_law", "get_links" and "search_legislation" (8 tools before, 10 now)
⟨36 unchanged words⟩ and the texts it amended or was amendedby.by (amended_by / amended: one entry per text and relation, with articles listing the articles of this law it touches, or of the other law for amended; no articles means the whole law). Use get_article to read one article's verbatim text ⟨34 unchanged words⟩
⟨34 unchanged words⟩ of only what get_law and get_article attach automatically. For a law key ("law/<id>") the default scope "all" includes the edges of its articles too (each link keeps its real to_key, e.g. "law/244611/art/37"); scope "law" is the law itself only. Newest first by the date of the text each edge comes from; page with offset and next_offset, total is the number of edges.
Changed the definition of "search_legislation"
⟨99 unchanged words⟩ says what was searched instead (searched_instead). A code named in the query ("قانون العقوبات 670", "أصول محاكمات مدنية صورية") narrows the articles to that code; when none of its articles holds the other words, articles_not_in_code names it and the articles listed are from other texts. Each law carries title_en, an unofficial English title ⟨24 unchanged words⟩
Changed the definition of "get_law", "get_ruling" and "search_legislation"
⟨53 unchanged words⟩ , or get_law_texts to read all of them. title_en is an unofficial English title (a model's rendering of the Arabic one); the Arabic title and text are official and more accurate. Not legal advice.
⟨24 unchanged words⟩ rulings exist only as a scanned file). pdf_url is the full judgment's scan on the Lebanese University's site: always give it to the user with any answer about the ruling, so they can open the original. Not legal advice.
Added "get_law_texts"; changed the definition of "get_article", "get_law" and "search_legislation" (7 tools before, 8 now)
⟨47 unchanged words⟩ the earlier one the Centre's site still shows. centre_error, when present, notes an error in the Centre's own text (one article repeating another, a stray letter); the text itself is left as published. The text is copied exactly from the database; ⟨59 unchanged words⟩
⟨12 unchanged words⟩ "the article's printed number, e.g. \"212\"or, \"12 مكرر\" or \"586-1\" (an article numbered under another; \"586 (1)\" works too)","type":"string"}},"required": ⟨4 unchanged words⟩
Changed the definition of "get_article"
⟨59 unchanged words⟩ exactly from the database; nothing here is AI-written. Laws with ids from 2000000000 are ones the Lebanese University has not published yet, read by machine from scans of the Official Gazette's pages (unofficial copies, page images on the law's page); where the two readings differ the text shows both as ⟦reading one | reading two⟧: quote neither as certain. Not legal advice.
Certificate recorded, valid to 2026-12-29
Authorization not required
Unknown → Live
First tool surface recorded: 7 tools (server version 1.0.0)
https://lebaneselegislation.com/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 12 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨50 unchanged words⟩ :50,"description":"at most this manyedgesedges. quote is cut to 600 characters when longer (quote_truncated: true); get_article has the full wording","maximum":200,"minimum":1,"type":"integer"},"offset":{"default":0,"description":"how many edges to skip (next_offset of the previous page)","minimum":0,"type":"integer"},"order":{"default":"newest","description":"by the date of the text the edge comes from (Gazette date, else issue date)","enum":["newest","oldest"],"type":"string"},"relation":{"description":"narrow to one relation ⟨5 unchanged words⟩ ", \"repeal\"); omit for all","type":"string"},"scope":{"description":"for a law key only: \"all\" (default) adds the edges to or from its articles, \"law\" is the law itself only","enum":["all","law"],"type":"string"}},"required":[ ⟨3 unchanged words⟩
⟨166 unchanged words⟩ are official and more accurate; cite the Arabic. A search of the gazette category with a bare year ("2025") lists that year's issues, and "22/2025" is issue 22 of 2025; to list texts by date use list_legislation instead. Not legal advice.
⟨52 unchanged words⟩ ":{"description":"only laws issued thisyearyear;(appliesforwhenthekindgazetteiscategory,\"laws\"onlyorissuesomitted)published this year","type":"integer"}},"required": ⟨3 unchanged words⟩
List Official Gazette issues by publication date, newest first, with the number of texts each carries (text_count) and where the issue comes from: source "centre" (the Lebanese University's Centre, whose issues stop about a year back) or "scans" (issues seen in Gazette scans, ids from 2000000000, which cover recent months). since and until accept YYYY, YYYY-MM or YYYY-MM-DD, inclusive; "everything since January 2025" is since "2025-01". Page with offset and next_offset. get_gazette_issue reads one issue's texts. Not legal advice.
List laws, decrees and decisions by date, newest first: for "everything published since January 2025" call with since "2025-01". The date is the publication date: the Official Gazette date, else the issue date (each entry's date, with gazette_number, gazette_date and gazette_issue_id). Recent texts come from machine readings of Gazette scans (ids from 2000000000, unofficial) because the Lebanese University's Centre lags about a year, so a recent period lists mostly those. since and until accept YYYY, YYYY-MM or YYYY-MM-DD, inclusive. kind narrows to one kind, in Arabic ("قانون", "مرسوم") or E…
⟨43 unchanged words⟩ Lebanese University's database, never an AI-written summary. A ruling hit's pdf_url is its full judgment's scan on the Lebanese University's site: always pass it on with any answer that cites the ruling. English words work too: they are read into Arabic through a glossary, matched against the unofficial English titles, and when nothing matches the result says what was searched instead (searched_instead). Each law carries title_en, an unofficial English title a model wrote from the Arabic title alone: the Arabic title and text are official and more accurate; cite the Arabic. Not legal advice.
⟨36 unchanged words⟩ {"description":"words to search for, Arabic, English or French, or a law's id"," ⟨23 unchanged words⟩
⟨10 unchanged words⟩ date, status), its table of contents (articlethenumberschapters: id, parent_id, depth, heading), its articles in order (number, and the section_id of the chapter each sits under) and the texts it amended or was amended by. Use get_article to read one article's verbatimtext.text, or get_law_texts to read all of them. Not legal advice.
⟨8 unchanged words⟩ court rulings, or Official Gazette issues, bykeyword.keyword: Arabic words, French words (articles the Centre published in French, andFrench.the codes' French or English names), or a law's numeric id. Returns verbatim snippets from the Lebanese University's database ⟨7 unchanged words⟩
⟨37 unchanged words⟩ :"words to search for, Arabic or French, or a law's id","type":"string"},"year":{ ⟨20 unchanged words⟩
Get the verbatim texts of a law's articles in order, a page at a time: for each article its number, section_id, note, and the same text fields as get_article (text_ar in force today, text_fr, centre_text_ar when an amendment replaced the wording, version, repealed). Follow next_offset until it is absent to read the whole law. Amendment history stays in get_article. Not legal advice.