Recherche fédérée pondérée par pertinence sur toutes les sources. Tool ONE-STOP quand on ne sait pas où chercher : interroge en parallèle les sources locales (DILA judic, JADE admin, LEGI, CEDH, CJUE) et retourne une liste fusionnée triée par score BM25 avec un bonus d'autorité (CE/Cass/CEDH > CA...
Risk signalsAccepts freeform code/query input (query) · Bulk/mass operation — affects multiple targets · Admin/system-level operation
Part of the Justicelibre server.
Free to start. No card required.
AI agents call search_all 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_all 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_all": {}
}
}See the full Justicelibre policy for all 30 tools.
These attack patterns abuse exactly the kind of access search_all 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.
Recherche fédérée pondérée par pertinence sur toutes les sources. Tool ONE-STOP quand on ne sait pas où chercher : interroge en parallèle les sources locales (DILA judic, JADE admin, LEGI, CEDH, CJUE) et retourne une liste fusionnée triée par score BM25 avec un bonus d'autorité (CE/Cass/CEDH > CAA > TA/CA). Args: query: mots-clés (ou phrase). Si expand_synonyms=True (défaut), les termes du thésaurus juridique FR sont automatiquement étendus à leurs équivalents (ex: "harcèlement" → aussi "intimidation", "vexation morale", etc.) sources: liste optionnelle parmi ["dila", "jade", "legi", "cedh", "cjue"]. None = toutes. sort: "relevance" (défaut) ou "date_desc" date_min, date_max: ISO YYYY-MM-DD limit: nombre de résultats fusionnés (défaut 30, max 100) expand_synonyms: active le thésaurus (défaut True) Returns: dict {"query_expanded", "per_source_counts", "results": [...]}. 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_all: 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_all 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_all 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_all. 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_all 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.