Construit l'URL canonique d'un document à partir de son identifiant. Utile pour vérifier les sources à la main sur le site officiel (Légifrance, Conseil constitutionnel, EUR-Lex, HUDOC, etc.) ou pour inclure un lien cliquable dans un courrier. Identifiants reconnus : - LEGIARTI* → Légifrance arti...
Part of the Justicelibre server.
Free to start. No card required.
AI agents invoke build_source_url to trigger processes or run actions in Justicelibre. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
build_source_url can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"build_source_url": {
"limits": [
{
"counter": "build_source_url_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Justicelibre policy for all 30 tools.
These attack patterns abuse exactly the kind of access build_source_url gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Construit l'URL canonique d'un document à partir de son identifiant. Utile pour vérifier les sources à la main sur le site officiel (Légifrance, Conseil constitutionnel, EUR-Lex, HUDOC, etc.) ou pour inclure un lien cliquable dans un courrier. Identifiants reconnus : - LEGIARTI* → Légifrance article (passer legitext du texte parent pour distinguer code (/codes/) vs loi non codifiée (/loda/) - LEGITEXT* / JORFTEXT* → texte entier Légifrance - JURITEXT* / CONSTEXT* / CETATEXT* → décisions Légifrance - CELEX (6XXXXCJXXXX) → EUR-Lex (CJUE) - ECLI:* → EUR-Lex deeplink - itemid HUDOC (001-XXXXXX) → Cour EDH - ArianeWeb (/Ariane_Web/AW_DCE/|XXXXXX) → conseil-etat.fr Args: identifier: l'ID à convertir legitext: (optionnel) LEGITEXT du texte parent si identifier est un LEGIARTI — améliore la précision de l'URL (codes/ vs loda/) date: (optionnel, YYYY-MM-DD) — appendé à l'URL Légifrance pour pointer vers la version de l'article en vigueur à cette date (ex: /loda/article_lc/LEGIARTI.../2023-01-01). Indispensable pour vérifier l'état du droit à une date historique, sinon Légifrance affiche la version courante même si l'article a été abrogé depuis. Returns: {"id", "source_url"} ou {"error"} si format non reconnu.. It is categorised as a Execute tool in the Justicelibre MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Justicelibre MCP server in PolicyLayer and add a rule for build_source_url: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Justicelibre. Nothing to install.
build_source_url is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the build_source_url rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for build_source_url. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
build_source_url is provided by the Justicelibre MCP server (https://justicelibre.org/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Justicelibre tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.