Soft-delete an inbox. It enters a 7-day grace period before permanent deletion.
AI agents call delete_inbox to permanently remove resources in Lobstermail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the deletion is soft (with a 7-day grace period), the tool permanently removes an inbox and its data once the grace period expires. This is an irreversible action on the specified inbox. The blast radius is significant—an AI agent misusing this could delete inboxes users depend on.
From the tool's definition Tool name is 'delete_inbox' and description states it 'Soft-delete an inbox' with a grace period before 'permanent deletion.' The tool removes an inbox and its contents.
Attacks that exploit this kind of access
Soft-delete an inbox. It enters a 7-day grace period before permanent deletion. It is categorised as a Destructive tool in the Lobstermail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lobstermail MCP server in PolicyLayer and add a rule for delete_inbox: 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 Lobstermail. Nothing to install.
delete_inbox 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_inbox 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_inbox. 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_inbox is provided by the Lobstermail MCP server (lobster-kit/mcp-server-lobstermail). 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 →