delete_agent
AI agents call delete_agent to permanently remove resources in Memanto MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible operation (deletion) on agent data. While the empty description reduces confidence slightly, the explicit 'delete' action in the name combined with the server's role in persistent memory management clearly indicates this is a destructive action that cannot be undone. High severity because deleting an agent could destroy long-term memory state and goal progress for that agent.
From the tool's definition Tool name is 'delete_agent' and the description is empty. The name explicitly indicates permanent deletion of an agent record. Given the context that this server manages persistent memory and agent state, deletion would irreversibly remove stored data.
Attacks that exploit this kind of access
delete_agent. It is categorised as a Destructive tool in the Memanto MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memanto MCP server in PolicyLayer and add a rule for 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 Memanto MCP. Nothing to install.
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 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 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.
delete_agent is provided by the Memanto MCP server (moorcheh-ai/memanto). 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 →