Delete a note (queued background write by default).
AI agents call notes_delete to permanently remove resources in Macnotes — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of notes is a destructive operation that cannot be undone. Even though the deletion is queued as a background write (which may offer some transactional safety), the ultimate effect is permanent removal of user data. This ranks higher than Write or Execute because data loss is irreversible.
From the tool's definition Tool name is 'notes_delete' and description states 'Delete a note' — this irreversibly removes data from Apple Notes.
Attacks that exploit this kind of access
Delete a note (queued background write by default). It is categorised as a Destructive tool in the Macnotes MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Macnotes MCP server in PolicyLayer and add a rule for notes_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 Macnotes. Nothing to install.
notes_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 notes_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 notes_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.
notes_delete is provided by the Macnotes MCP server (zorrobyte/macnotes-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 →