Permanently delete a squad.
AI agents call vapi_delete_squad to permanently remove resources in Mcp Vapi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs a permanent, non-reversible deletion of a squad resource. This fits the Destructive category definition (irreversibly deletes data that cannot be undone). Severity is high because deletion of a squad likely impacts multiple dependent resources (assistants, calls, configurations) and cannot be recovered without backups.
From the tool's definition Tool name contains 'delete' and description states 'Permanently delete a squad' — this is an irreversible deletion operation.
Attacks that exploit this kind of access
Permanently delete a squad. It is categorised as a Destructive tool in the Mcp Vapi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Vapi MCP server in PolicyLayer and add a rule for vapi_delete_squad: 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 Mcp Vapi. Nothing to install.
vapi_delete_squad 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 vapi_delete_squad 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 vapi_delete_squad. 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.
vapi_delete_squad is provided by the Mcp Vapi MCP server (adhirajhangal/mcp-vapi). 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 →