Archive an agent (soft delete). The agent is hidden from list_agents but preserved for task history. Use unarchive_agent to restore. Resolve by id or name.
AI agents call delete_agent to permanently remove resources in Todos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While soft deletes are technically reversible through unarchive_agent, the action fundamentally and irreversibly transitions an agent to a hidden/archived state in active workflows. This removes it from normal visibility and operations, making it a destructive action. The reversibility mechanism exists but requires a separate explicit action, placing this in Destructive rather than Write.
From the tool's definition Tool performs 'soft delete' via 'Archive an agent' operation. Although reversible via unarchive_agent, the primary action irreversibly removes the agent from active use (hidden from list_agents).
Attacks that exploit this kind of access
Archive an agent (soft delete). The agent is hidden from list_agents but preserved for task history. Use unarchive_agent to restore. Resolve by id or name. It is categorised as a Destructive tool in the Todos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todos 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 Todos. 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 Todos MCP server (@hasna/todos). 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 →