Delete a persona permanently
AI agents call delete_persona to permanently remove resources in Tavus MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a persona object from the Tavus system. Permanent deletion is irreversible and constitutes destructive action. While not directly damaging financial systems or executing arbitrary code, the permanent loss of a persona (which likely represents configured AI entity state, settings, or associated media) cannot be recovered.
From the tool's definition 'Delete a persona permanently' indicates irreversible removal of data without undo capability. The verb 'delete' combined with 'permanently' is explicit destructive action language.
Attacks that exploit this kind of access
Delete a persona permanently. It is categorised as a Destructive tool in the Tavus MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tavus MCP Server MCP server in PolicyLayer and add a rule for delete_persona: 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 Tavus MCP Server. Nothing to install.
delete_persona 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 delete_persona 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 delete_persona. 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.
delete_persona is provided by the Tavus MCP Server MCP server (rakeshdavid/tavus-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 →