judilibre_rechercher
AI agents call judilibre_rechercher to retrieve information from Mpc Judilibre without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves judicial decisions from a public open-data repository. Search operations are non-destructive read operations with no side effects. Confidence is slightly lowered (0.85 vs higher) due to empty description, but server context and naming pattern provide strong evidence of read-only functionality.
From the tool's definition Tool name is 'judilibre_rechercher' (search in French); server provides access to open data judicial decisions from JUDILIBRE API; sibling tools include 'judilibre_decision', 'judilibre_export', 'judilibre_stats', 'judilibre_scan' which are all read-only…
Attacks that exploit this kind of access
judilibre_rechercher. It is categorised as a Read tool in the Mpc Judilibre MCP Server, which means it retrieves data without modifying state.
Register the Mpc Judilibre MCP server in PolicyLayer and add a rule for judilibre_rechercher: 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 Mpc Judilibre. Nothing to install.
judilibre_rechercher 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 judilibre_rechercher 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 judilibre_rechercher. 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.
judilibre_rechercher is provided by the Mpc Judilibre MCP server (ktulu-analog/mcp-judilibre). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →