sendook_delete_inbox
AI agents call sendook_delete_inbox to permanently remove resources in Sendook — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting an inbox is an irreversible action that destroys data and cannot be undone. This falls squarely into the Destructive category. The high severity reflects the potential for significant data loss if an AI agent misuses this tool—an entire inbox with potentially important emails could be permanently removed.
From the tool's definition Tool name is 'sendook_delete_inbox' which explicitly indicates deletion of an inbox resource. The tool description is empty, but the name combined with the server's email communication platform context makes the destructive nature clear.
Attacks that exploit this kind of access
sendook_delete_inbox. It is categorised as a Destructive tool in the Sendook MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sendook MCP server in PolicyLayer and add a rule for sendook_delete_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 Sendook. Nothing to install.
sendook_delete_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 sendook_delete_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 sendook_delete_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.
sendook_delete_inbox is provided by the Sendook MCP server (streamlinedstartup/sendook-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 →