Delete a single sandbox message
AI agents call delete-sandbox-message 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.
The tool performs a delete operation that cannot be undone. Even though it operates on sandbox (test) data rather than production, deletion is inherently a destructive action. The high severity reflects that an AI agent could permanently remove messages from a user's inbox, causing data loss. Sandbox context reduces real-world impact compared to production deletion, but the destructive nature remains.
From the tool's definition Tool name 'delete-sandbox-message' and description 'Delete a single sandbox message' indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a single sandbox message. 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 delete-sandbox-message: 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.
delete-sandbox-message 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-sandbox-message 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-sandbox-message. 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-sandbox-message 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 →