Cancel a scheduled meeting for an employee.
AI agents call cancel_meeting to permanently remove resources in HR Assistant Agent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a meeting removes it from all attendees' schedules. This action is generally not reversible (the meeting slot and any associated invitations/notifications are gone), placing it in the Destructive category. Severity is medium because the blast radius affects meeting participants and organizational scheduling, but does not destroy sensitive data or financial records.
From the tool's definition "Cancel a scheduled meeting" — cancellation is an irreversible removal of a scheduled event
Attacks that exploit this kind of access
Cancel a scheduled meeting for an employee. It is categorised as a Destructive tool in the HR Assistant Agent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the HR Assistant Agent MCP server in PolicyLayer and add a rule for cancel_meeting: 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 HR Assistant Agent. Nothing to install.
cancel_meeting is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cancel_meeting 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 cancel_meeting. 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.
cancel_meeting is provided by the HR Assistant Agent MCP server (nishu8875/hr-assistant-agent). 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 →