Delete a sending domain (Sidemail API)
AI agents call delete-domain to permanently remove resources in Sidemail MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a domain is a destructive action that cannot be undone. It removes email sending infrastructure and configuration, potentially disrupting email operations. While not financial in nature, this represents irreversible data loss and operational impact, placing it in the Destructive category with high severity.
From the tool's definition Tool name is 'delete-domain' and description states 'Delete a sending domain'. The verb 'delete' indicates irreversible removal of infrastructure data.
Attacks that exploit this kind of access
Delete a sending domain (Sidemail API). It is categorised as a Destructive tool in the Sidemail MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sidemail MCP Server MCP server in PolicyLayer and add a rule for delete-domain: 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 Sidemail MCP Server. Nothing to install.
delete-domain 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-domain 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-domain. 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-domain is provided by the Sidemail MCP Server MCP server (sidemail/sidemail-mcp-server). 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 →