Delete an email from Outlook.
AI agents call mail_delete to permanently remove resources in Outpost — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Email deletion permanently removes data with no undo capability. The blast radius is high if an AI agent misuses this tool (e.g., deleting important emails, phishing emails, or entire conversations). This is categorized as Destructive rather than Write because the action cannot be reversed and destroys existing data rather than creating or modifying it.
From the tool's definition Tool description explicitly states 'Delete an email from Outlook' — deletion is irreversible and constitutes destruction of data.
Attacks that exploit this kind of access
Delete an email from Outlook. It is categorised as a Destructive tool in the Outpost MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Outpost MCP server in PolicyLayer and add a rule for mail_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 Outpost. Nothing to install.
mail_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 mail_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 mail_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.
mail_delete is provided by the Outpost MCP server (signalclaude/outpost). 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 →