Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Fontes 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
Live court decisions and legislation from court and government websites in 120+ jurisdictions.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user fontes-mcp '--' uvx fontes-mcp
# 2 — ask your agent for something these tools do
# list_jurisdictions, search_caselaw, get_decision and 5 more
Fontes 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 Fontes 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 uv (docs.astral.sh/uv): uvx 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 fontes-mcp '--' uvx fontes-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take WLM_FR_PISTE_CLIENT_ID (France only: client ID of a free PISTE app subscribed to Judilibre and Légifrance. France is off without it.), WLM_FR_PISTE_CLIENT_SECRET (France only: client secret of the same PISTE app.), WLM_US_GOVINFO_KEY (United States only: free api.data.gov key for case-law search (without it, about 10 searches a day).) if you want to set them.
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.
8 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.
List the jurisdictions this server covers. Call this first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | optional text to narrow the list (matches code, alias or name, e.g. "nl", "united", "netherlands"). An exact code, alias or name gives that jurisdiction in full; many matches give a compact index. |
Search court decisions (case law / precedent) in one jurisdiction.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb" (alias "uk"). |
| query | string | no | search words in the language of the source (Dutch for nl, English for gb). May be empty ("") for sources that can list by filters alone (date, court, number). Date, court, type, year and similar narro |
| limit | integer | no | results per page (default 10). |
| page | integer | no | 1-based page number. |
| filters | object | no | optional jurisdiction-specific filters as a dict, e.g. {"sort": "uitspraak", "period": "dit_jaar"} for nl or {"court": "uksc,ewca/civ", "order": "-date"} for gb. The valid names differ per jurisdictio |
Fetch one court decision as markdown (metadata, summary, full text, source URL).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb". |
| id | string | yes | the identifier the source uses, as returned by search_caselaw. nl: ECLI ("ECLI:NL:HR:2024:123"). gb: neutral citation ("[2024] UKSC 1", "[2026] EWHC 2093 (Ch)") or Find Case Law slug ("uksc/2024/1"). |
| max_chars | integer | no | page size (default 60000). Long decisions end with a note giving the next offset. |
| offset | integer | no | character offset to continue from (from that note). |
Find laws, acts and statutory instruments in one jurisdiction.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb". |
| query | string | no | (may be empty "" when filters alone select) words from the title (or full text where the source allows), in the source's language, e.g. "huurprijzen woonruimte" (nl), "Companies Act 2006" (gb). nl als |
| limit | integer | no | results per page (default 20). |
| page | integer | no | 1-based page number. |
| filters | object | no | optional jurisdiction-specific filters as a dict, e.g. {"current_only": false} for nl or {"search_in": "text", "doc_type": "ukpga"} for gb. See list_jurisdictions. |
Table of contents of a law (parts, chapters, articles/sections) with provision labels.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb". |
| id | string | yes | law id from search_legislation. nl: BWB-id ("BWBR0005289"). gb: type/year/number ("ukpga/2006/46"). |
| keyword | string | no | optional; only list provisions whose number/title starts a word with (else contains) this text, case-insensitive. It does NOT search the body text. Strongly recommended for big codes. |
Text of one article / section / regulation / schedule paragraph.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb". |
| id | string | yes | law id from search_legislation (nl "BWBR0005289", gb "ukpga/2006/46"). |
| provision | string | yes | nl: article number ("2", "6:2", "Artikel 7a"). gb: "172", "s.172", "section/172", "reg 3", "sch 1 para 2", "schedule/1/paragraph/2". |
Full consolidated (current) text of a law as markdown, pageable.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | code from list_jurisdictions, e.g. "nl", "gb". |
| id | string | yes | law id from search_legislation. |
| max_chars | integer | no | page size (default 60000). Big codes run to megabytes; prefer get_legislation_toc + get_legislation_provision. |
| offset | integer | no | character offset to continue from (from the truncation note). |
Prepare a bug report about Fontes for its developers. Only when the user asks to report a problem.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| note | string | no | what went wrong, in the user's words. Do not copy document text, search terms or client details into it unless the user explicitly asks you to. |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Fontes 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.
Tools were statically extracted from the published source (8 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
tests/live/test_sn.py (2 KB) was not read: over the file-count budget.
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 |
|---|---|---|
| list_jurisdictions | no tags | |
| search_caselaw | untrusted-input | untrusted-input: keyword "fetch" |
| get_decision | untrusted-input | untrusted-input: keyword "fetch" |
| search_legislation | no tags | |
| get_legislation_toc | no tags | |
| get_legislation_provision | no tags | |
| get_legislation_text | no tags | |
| report_bug | no tags |
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 Fontes 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.