Vérifie que l'API JUDILIBRE est opérationnelle.
AI agents call judilibre_healthcheck 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 is a diagnostic/monitoring tool that performs a simple read-only health check. It retrieves status information about the API's availability with no side effects, no data modification, and no execution of arbitrary code. It poses minimal security risk as it only queries system state.
From the tool's definition Tool name 'judilibre_healthcheck' and description 'Vérifie que l'API JUDILIBRE est opérationnelle' (Verifies that the JUDILIBRE API is operational) indicate a status-check operation that queries the operational state of an API without modifying, executing, or…
Attacks that exploit this kind of access
Vérifie que l'API JUDILIBRE est opérationnelle. 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_healthcheck: 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_healthcheck 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_healthcheck 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_healthcheck. 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_healthcheck 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 →