Get leave history for the employee
AI agents call get_leave_history to retrieve information from LeaveManager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical leave data for an employee. It performs a passive data query with no capability to modify, delete, or execute any operations. The absence of destructive, financial, or executable operations, combined with the explicit read semantics, places it squarely in the Read category with low severity, as misuse would only expose historical information without enabling harmful modifications.
From the tool's definition The tool is named "get_leave_history" and described as "Get leave history for the employee" - both indicate a retrieval operation without any modification or side effects. The action verb "Get" is a read-only operation that queries historical data.
Attacks that exploit this kind of access
Get leave history for the employee. It is categorised as a Read tool in the LeaveManager MCP Server, which means it retrieves data without modifying state.
Register the LeaveManager MCP server in PolicyLayer and add a rule for get_leave_history: 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 LeaveManager. Nothing to install.
get_leave_history 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 get_leave_history 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 get_leave_history. 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.
get_leave_history is provided by the LeaveManager MCP server (umamaheswararao04/leavemanager-mcp-server). 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 →