Cherche les décisions qui citent EXPLICITEMENT un article de loi donné. Exploite l'index FTS5 sur les sources jurisprudence disponibles pour matcher les formulations courantes de citation ("article 1382 du code civil", "art. L. 1152-1 du Code du travail", etc.). Cross-référencement inverse : part...
Risk signalsAccepts freeform code/query input (code)
Part of the Justicelibre server.
Free to start. No card required.
AI agents call search_decisions_citing to retrieve information from Justicelibre without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though search_decisions_citing only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"search_decisions_citing": {}
}
}See the full Justicelibre policy for all 30 tools.
These attack patterns abuse exactly the kind of access search_decisions_citing gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Cherche les décisions qui citent EXPLICITEMENT un article de loi donné. Exploite l'index FTS5 sur les sources jurisprudence disponibles pour matcher les formulations courantes de citation ("article 1382 du code civil", "art. L. 1152-1 du Code du travail", etc.). Cross-référencement inverse : partant d'un article, on trouve la jurisprudence pertinente. LIMITATION CONNUE : ce tool trouve UNIQUEMENT les citations explicites du numéro d'article. Il ne capte PAS : - les références indirectes ("conformément aux dispositions du Code civil relatives à la responsabilité délictuelle…") - les renvois à une section entière sans numéro précis - les citations du code par abréviation seule sans article ("en vertu du CT") Pour une recherche conceptuelle plus large, préférer search_all avec l'expansion thésaurus (ex: "harcèlement" → inclut "intimidation" etc.). Args: code: code court de l'article (ex : "CT", "CC") num: numéro de l'article (ex : "L1152-1", "1240") sources: liste optionnelle de sources à interroger parmi ["dila", "jade", "cedh", "cjue"]. Par défaut : toutes. limit: nombre de décisions par source (défaut 20, max 50) Returns: dict {"code", "num", "total", "per_source": {source: count}, "decisions": [{source, id, juridiction, date, title, extract}]}. It is categorised as a Read tool in the Justicelibre MCP Server, which means it retrieves data without modifying state.
Register the Justicelibre MCP server in PolicyLayer and add a rule for search_decisions_citing: 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.
search_decisions_citing is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_decisions_citing 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 search_decisions_citing. 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.
search_decisions_citing 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.