Delete a custom app from the clock.
AI agents call delete_custom_app to permanently remove resources in Ulanzi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes custom applications from the device without the ability to undo the action. While the blast radius is limited to a single device's custom apps (not system-critical), deletion is inherently destructive and irreversible. Severity is medium rather than high because the impact is scoped to one user's custom configurations on a single device, not widespread data loss or system compromise.
From the tool's definition Tool name contains 'delete' and description states 'Delete a custom app from the clock' - irreversible removal of user-created application data.
Attacks that exploit this kind of access
Delete a custom app from the clock. It is categorised as a Destructive tool in the Ulanzi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ulanzi MCP server in PolicyLayer and add a rule for delete_custom_app: 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 Ulanzi. Nothing to install.
delete_custom_app 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_custom_app 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_custom_app. 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_custom_app is provided by the Ulanzi MCP server (jelloeater/ulanzi-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 →