Move messages to Trash (recoverable 30 days). NOT permanent delete.
AI agents call delete to permanently remove resources in Nexus Core — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the action is recoverable within 30 days, moving messages to Trash is effectively a destructive operation — data is removed from its original location and inaccessible in normal flow. The most severe applicable category is Destructive, but severity is medium rather than high/critical due to the recovery window.
From the tool's definition 'Move messages to Trash' and 'delete' in the tool name indicate removal of data; however, 'recoverable 30 days' and 'NOT permanent delete' mitigate full irreversibility.
Attacks that exploit this kind of access
Move messages to Trash (recoverable 30 days). NOT permanent delete. It is categorised as a Destructive tool in the Nexus Core MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nexus Core MCP server in PolicyLayer and add a rule for 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 Nexus Core. Nothing to install.
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 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 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.
delete is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →