Delete a note by its ID. This action is permanent and cannot be undone.
AI agents call kura_delete to permanently remove resources in KURA Notes MCP Client — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly deletes data (notes) and explicitly states the action cannot be undone. This meets the definition of Destructive category. Severity is high because deletion of user notes represents significant data loss, though the blast radius is limited to individual notes rather than system-wide data. High confidence due to explicit language confirming permanent deletion.
From the tool's definition Delete a note by its ID. This action is permanent and cannot be undone.
Attacks that exploit this kind of access
Delete a note by its ID. This action is permanent and cannot be undone. It is categorised as a Destructive tool in the KURA Notes MCP Client MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KURA Notes MCP Client MCP server in PolicyLayer and add a rule for kura_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 KURA Notes MCP Client. Nothing to install.
kura_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 kura_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 kura_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.
kura_delete is provided by the KURA Notes MCP Client MCP server (tillmatthis/kura-notes-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 →