Delete a voice agent from your account.
AI agents call retell_delete_agent to permanently remove resources in Retell AI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of an agent is an irreversible destructive action that cannot be undone. Once deleted, the agent configuration and associated metadata are removed from the account. This qualifies as Destructive rather than Execute because the action's primary purpose is permanent data removal, not conditional execution of logic.
From the tool's definition Tool name explicitly contains 'delete' and description states 'Delete a voice agent from your account' — irreversible removal of a configured agent resource.
Attacks that exploit this kind of access
Delete a voice agent from your account. It is categorised as a Destructive tool in the Retell AI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Retell AI MCP Server MCP server in PolicyLayer and add a rule for retell_delete_agent: 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 Retell AI MCP Server. Nothing to install.
retell_delete_agent 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 retell_delete_agent 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 retell_delete_agent. 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.
retell_delete_agent is provided by the Retell AI MCP Server MCP server (itsanamune/retellsimp). 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 →