Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/capazme/mcp-legal-itWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/capazme/mcp-legal-it/plugin)<a href="https://agentmods.dev/plugins/capazme/mcp-legal-it/plugin"><img src="https://agentmods.dev/badge/plugins/capazme/mcp-legal-it/plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/capazme/mcp-legal-it/plugin"><img src="https://agentmods.dev/badge/plugins/capazme/mcp-legal-it/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
legal-it scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "legal-it",
"version": "2.16.0",
"description": "Plugin legale italiano completo: 228 tool di calcolo e ricerca, normativa (Normattiva/EUR-Lex/Brocardi/Gazzetta Ufficiale), giurisprudenza (Cassazione, Corte Costituzionale, CeRDEF tributario, TAR/CdS, CGUE), orientamenti e contrasti, recepimento UE→IT, verifica citazioni, CONSOB, compliance GDPR, diritto del lavoro, crisi d'impresa, societario, export DOCX/PDF. 23 skill, 10 slash command, 6 agenti specializzati.",
"author": {
"name": "capazme"
},
"homepage": "https://github.com/capazme/mcp-legal-it",
"repository": "https://github.com/capazme/mcp-legal-it",
"license": "Apache-2.0",
"keywords": [
"legal",
"italian-law",
"GDPR",
"normattiva",
"cassazione",
"avvocato"
]
}
What it installs
The manifest is a name and a version. 23 skills, 10 commands, 6 agents, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 2,856 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cookie-audit A 248 tokens
- Skill analisi-fornitori A 209 tokens
- Skill esporta-documento A 157 tokens
- Skill procure-quotazioni A 181 tokens
- Skill analisi-giurisprudenziale A 55 tokens
- Skill analisi-sinistro A 87 tokens
- Skill genera-atto A 129 tokens
- Skill parere-legale A 56 tokens
- Skill compliance-privacy A 75 tokens
- Skill analisi-articolo A 71 tokens
- Skill analisi-delibere-consob A 93 tokens
- Skill causa-civile A 79 tokens
- Skill pianificazione-successione A 69 tokens
- Skill recupero-credito A 80 tokens
- Skill redazione-contratto A 57 tokens
- Skill calcolo-parcella A 79 tokens
- Skill confronto-norme A 72 tokens
- Skill data-breach A 60 tokens
- Skill mappatura-normativa A 76 tokens
- Skill novita-consob A 72 tokens
- Skill quantificazione-danni A 67 tokens
- Skill ricerca-normativa A 73 tokens
- Skill verifica-prescrizione A 72 tokens
- Command release A 56 tokens
- Command digest A 51 tokens
- Command dati A 33 tokens
- Command verbale A 31 tokens
- Command scadenza A 14 tokens
- Command privacy A 73 tokens
- Command interessi A 16 tokens
- Command norma A 41 tokens
- Command codice-fiscale A 15 tokens
- Command sentenza A 16 tokens
- Agent ricerca-giurisprudenziale A 42 tokens
- Agent digest-giuridico A 81 tokens
- Agent penalista A 38 tokens
- Agent redattore-atti A 51 tokens
- Agent civilista A 40 tokens
- Agent privacy-specialist A 41 tokens
- Hook Stop A not measured
- MCP server legal-it A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed f74090a1cf18
- 13d ago Changed 235803051fea
- 16d ago Changed 8a70ff8e9059
- 18d ago Changed 52059c4822ec
- 19d ago Changed 72dd1313f39d
- 22d ago Changed eaf27eb6d5f4
- 23d ago Changed d71471964d28
- 26d ago Changed 129a69871350
- 1mo ago First seen · 20 lines scan A d4af783a1bc0
legal-it is a plugin published in the GitHub repository capazme/mcp-legal-it (24 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
korean-law
A set of tools for researching South Korean law through the Ministry of Government Legislation’s data services. It covers laws, court decisions, administrative rules, local regulations, treaties, and legal interpretations.
korean-law-marketplace
Plugin marketplace listing 1 plugin: korean-law.
ceza-hukuku-ozel
TCK özel hükümler: kişilere karşı (yaralama, tehdit, hakaret), malvarlığına karşı (hırsızlık, dolandırıcılık, güveni kötüye kullanma), kamu idaresine ve güvene karşı suçların unsurları ve nitelikli halleri.
cevre-hukuku
Çevre hukuku: 2872 sayılı Kanun — ÇED süreci ve iptali, çevre izin ve lisansları, kirletenin sorumluluğu, idari yaptırımlar; çevresel uyuşmazlıklarda idari ve adli yargı yolları.
synapsor
Turn one application data change into a disabled, reviewable Synapsor Safe Action without giving the Cursor agent SQL or commit authority.
droit-francais-skill
Méthodologie rigoureuse de recherche en droit français, distribuée comme plugin Claude Code : sources primaires Légifrance et Judilibre, vérification de vigueur, citations traçables.