AI agents call list_leaves to retrieve information from Eyeot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing leave request records. It performs no data modification, deletion, or external operations. While leave request data may contain personal/HR information, the action itself is a simple read operation with minimal blast radius if misused by an AI agent—the worst outcome would be unauthorized viewing of leave records, not system-wide damage or financial impact.
From the tool's definition Tool name 'list_leaves' combined with description 'Lister les demandes de congés' (List leave requests). The verb 'list' is a query operation that retrieves leave request data without modification or side effects.
Attacks that exploit this kind of access
Lister les demandes de congés. It is categorised as a Read tool in the Eyeot MCP Server, which means it retrieves data without modifying state.
Register the Eyeot MCP server in PolicyLayer and add a rule for list_leaves: 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 Eyeot. Nothing to install.
list_leaves 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 list_leaves 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 list_leaves. 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.
list_leaves is provided by the Eyeot MCP server (https://erp.eyeot.fr/api/v1/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 →