Delete a saved preset.
AI agents call delete_preset to permanently remove resources in Sushi MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (a preset configuration). While the blast radius is limited to audio presets rather than critical system data, deletion cannot be undone and represents a destructive operation. Severity is medium rather than high because presets are typically recoverable through backup or recreation, and affect only audio configuration rather than financial or system-critical resources.
From the tool's definition Tool name is 'delete_preset' with description 'Delete a saved preset.' The verb 'delete' is explicit and irreversible.
Attacks that exploit this kind of access
Delete a saved preset. It is categorised as a Destructive tool in the Sushi MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sushi MCP Server MCP server in PolicyLayer and add a rule for delete_preset: 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 Sushi MCP Server. Nothing to install.
delete_preset 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_preset 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_preset. 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_preset is provided by the Sushi MCP Server MCP server (nagarjun226/sushi-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 →