Permanently delete a session (history + sandbox). Cannot delete a running session.
AI agents call session_delete to permanently remove resources in Managed Agent Control — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes session data including history and sandbox environment. While not the most severe threat (no financial impact, no code execution), permanent deletion of managed agent sessions cannot be undone and could result in loss of critical interaction records and computational environments.
From the tool's definition Tool description states 'Permanently delete a session (history + sandbox)' — the word 'Permanently' and 'delete' indicate irreversible data destruction.
Attacks that exploit this kind of access
Permanently delete a session (history + sandbox). Cannot delete a running session. It is categorised as a Destructive tool in the Managed Agent Control MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Managed Agent Control MCP server in PolicyLayer and add a rule for session_delete: 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 Managed Agent Control. Nothing to install.
session_delete 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 session_delete 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 session_delete. 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.
session_delete is provided by the Managed Agent Control MCP server (modus-agendi/managed-agent-control-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 →