judilibre_taxonomie
AI agents call judilibre_taxonomie 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.
The tool appears to retrieve or query taxonomy/classification information from the JUDILIBRE judicial database. Given the server's purpose (exposing French law data via PISTE platform) and the presence of other read-only tools, this is categorized as Read. Confidence is moderate (0.7) due to missing description; if the tool actually modified taxonomies or executed complex queries, this could be Execute instead.
From the tool's definition Tool name 'judilibre_taxonomie' and context of JUDILIBRE API (open data judicial decisions) suggest querying taxonomy or classification data.
Attacks that exploit this kind of access
judilibre_taxonomie. 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_taxonomie: 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_taxonomie 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_taxonomie 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_taxonomie. 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_taxonomie 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 →