Deletes a Retell LLM
AI agents call delete_retell_llm to permanently remove resources in Retellai — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a Retell LLM resource. Deletion is an irreversible operation that cannot be undone, making it Destructive rather than Write. The blast radius is high because deleting an LLM could break dependent agents, phone calls, or workflows that rely on that LLM configuration. An AI agent misusing this could disable critical conversational AI infrastructure.
From the tool's definition Tool name is 'delete_retell_llm' and description states 'Deletes a Retell LLM'. The verb 'delete' and the action of removing an LLM configuration are irreversible operations.
Attacks that exploit this kind of access
Deletes a Retell LLM. It is categorised as a Destructive tool in the Retellai MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Retellai MCP server in PolicyLayer and add a rule for delete_retell_llm: 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 Retellai. Nothing to install.
delete_retell_llm 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_retell_llm 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_retell_llm. 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_retell_llm is provided by the Retellai MCP server (@abhaybabbar/retellai-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 →