Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants.
Cedarlaw is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Lebanese legislation corpus: laws, articles, rulings and Gazette issues, verbatim.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user cedarlaw-mcp '--' npx -y @reneturcios/cedarlaw mcp
# 2 — ask your agent for something these tools do
# search_legislation, get_law, get_article and 7 more
Cedarlaw costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Cedarlaw as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user cedarlaw-mcp '--' npx -y @reneturcios/cedarlaw mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Search Lebanese legislation (laws, decrees, decisions), their articles, court rulings, or Official Gazette issues, by keyword: Arabic words, French words (articles the Centre published in French, and the codes' French or English names), or a law's numeric id. Returns verbatim snippets from the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | words to search for, Arabic, English or French, or a law's id |
| kind | string | no | narrow to one category; omit to search all four |
| year | integer | no | only laws issued this year; for the gazette category, only issues published this year |
| limit | integer | no | results per category, at most 20 |
Get a law, decree or similar text's metadata (kind, number, date, status), its table of contents (the chapters: 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 (amended_by / amended: one…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | the law's numeric id, from search_legislation or its URL |
Get one article's verbatim Arabic text as in force today (and French, when the Centre published it and no amendment has replaced it), its in-force status, amendment history, and the canonical and source URLs. When an amendment replaced the wording, text_ar is the new wording and centre_text_ar the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| law_id | integer | yes | the law's id (see get_law) |
| number | string | yes | the article's printed number, e.g. "212", "12 مكرر" or "586-1" (an article numbered under another; "586 (1)" works too) |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| law_id | integer | yes | the law's numeric id |
| offset | integer | no | how many articles to skip (next_offset of the previous page) |
| limit | integer | no | articles per page, at most 200 |
Get one court ruling (judgment) by id: court, number, date, panel, and its verbatim text when the Centre holds it as typed text. When available, pages returns the scanned judgment's machine reading, with low_confidence: true on hard-to-read pages where errors are expected. pdf_url is the full…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | the ruling's numeric id, from search_legislation |
Get one Official Gazette issue by id: its number, publication date, and the laws, decrees and decisions it published. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | the issue's numeric id, from search_legislation |
Get the graph edges into or out of one item: a law, an article, a ruling, an opinion, a research study or a Gazette issue. Use this to walk citations and amendments directly, instead of only what get_law and get_article attach automatically. For a law key ("law/<id>") the default scope "all"…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | the item's key: "law/<id>", "law/<id>/art/<number>", "ruling/<id>", "opinion/<id>", "research/<id>" or "gazette/<id>" |
| direction | string | no | "to" (edges that name this item as their target) or "from" (edges this item itself carries) |
| relation | string | no | narrow to one relation (e.g. "cites", "amend", "repeal"); omit for all |
| scope | string | no | for a law key only: "all" (default) adds the edges to or from its articles, "law" is the law itself only |
| order | string | no | by the date of the text the edge comes from (Gazette date, else issue date) |
| offset | integer | no | how many edges to skip (next_offset of the previous page) |
| limit | integer | no | at most this many edges. quote is cut to 600 characters when longer (quote_truncated: true); get_article has the full wording |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | first date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD (e.g. "2025-01") |
| until | string | no | last date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD |
| kind | string | no | the kind of text, Arabic or English (e.g. "قانون" or "Law", "Decree") |
| order | string | no | by publication date |
| offset | integer | no | how many texts to skip (next_offset of the previous page) |
| limit | integer | no | texts per page, at most 100 |
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,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | first date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD |
| until | string | no | last date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD |
| order | string | no | by publication date |
| offset | integer | no | how many issues to skip (next_offset of the previous page) |
| limit | integer | no | issues per page, at most 100 |
Get the general repeals that may touch a law: earlier texts with a "all provisions contrary to this law are repealed" clause pointing at it. A list to check, never a finding that anything was actually repealed. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| law_id | integer | yes | the law's numeric id |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Cedarlaw or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Cedarlaw can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.