Estime l
AI agents call simuler_chomage to retrieve information from French Admin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to estimate unemployment benefits based on user inputs, a read-only operation that queries calculations but does not create, modify, delete, or execute external operations. The truncated description limits full certainty, but the use of 'simuler' and 'Estime' strongly indicates a read-only informational tool for French unemployment (chômage) benefit estimation.
From the tool's definition Tool name 'simuler_chomage' indicates simulation/estimation (simuler = to simulate). Description truncated but 'Estime' (estimates) suggests a calculation or projection tool that retrieves information without modifying data.
Attacks that exploit this kind of access
Estime l. It is categorised as a Read tool in the French Admin MCP Server, which means it retrieves data without modifying state.
Register the French Admin MCP server in PolicyLayer and add a rule for simuler_chomage: 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 French Admin. Nothing to install.
simuler_chomage 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 simuler_chomage 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 simuler_chomage. 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.
simuler_chomage is provided by the French Admin MCP server (mcp-tools-lab/french-admin-mcp). 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 →