Permanently delete a message and its attachments.
AI agents call mailosaur_messages_delete to permanently remove resources in Mailosaur MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes messages and associated files from the Mailosaur service. Once deleted, data cannot be recovered. This is a classic destructive operation. Severity is high because an AI agent could be tricked into deleting important test messages, user communications, or audit trails needed for compliance.
From the tool's definition Tool name and description explicitly state 'Permanently delete a message and its attachments' — permanent deletion is irreversible data destruction.
Attacks that exploit this kind of access
Permanently delete a message and its attachments. It is categorised as a Destructive tool in the Mailosaur MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mailosaur MCP server in PolicyLayer and add a rule for mailosaur_messages_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 Mailosaur MCP. Nothing to install.
mailosaur_messages_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 mailosaur_messages_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 mailosaur_messages_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.
mailosaur_messages_delete is provided by the Mailosaur MCP server (mrnewdelhi/mailosaur-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 →