Delete all messages from a sandbox inbox without deleting the inbox itself
AI agents call clean-sandbox-inbox to permanently remove resources in Mcp Mailtrap — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (emails) that cannot be recovered. Although scoped to a sandbox environment (which typically implies lower production impact), deletion operations are inherently destructive and irreversible. The severity is 'high' rather than 'critical' because sandbox inboxes are generally non-production; however, it remains destructive because deletion cannot be undone.
From the tool's definition Tool description explicitly states 'Delete all messages from a sandbox inbox' — the word 'Delete' combined with 'all messages' indicates irreversible data destruction.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Delete all messages from a sandbox inbox without deleting the inbox itself. It is categorised as a Destructive tool in the Mcp Mailtrap MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Mailtrap MCP server in PolicyLayer and add a rule for clean-sandbox-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 Mcp Mailtrap. Nothing to install.
clean-sandbox-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 clean-sandbox-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 clean-sandbox-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.
clean-sandbox-inbox is provided by the Mcp Mailtrap MCP server (mcp-mailtrap). 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 →