Delete a unit by UUID.
AI agents call delete_unit to permanently remove resources in Mcp Mealie — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a unit record from the Mealie system. While the blast radius is limited to a single unit entity (not cascading to critical data like recipes or meal plans), the action is irreversible. In a culinary/recipe management system, units are foundational taxonomy (e.g., cups, grams, liters). Deleting a unit could orphan recipes or meal plans that depend on it, causing data integrity issues.
From the tool's definition Tool name is 'delete_unit' with description 'Delete a unit by UUID.' The verb 'delete' and explicit irreversible data removal action classify this as Destructive.
Attacks that exploit this kind of access
Delete a unit by UUID. It is categorised as a Destructive tool in the Mcp Mealie MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Mealie MCP server in PolicyLayer and add a rule for delete_unit: 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 Mcp Mealie. Nothing to install.
delete_unit 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_unit 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_unit. 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_unit is provided by the Mcp Mealie MCP server (obrien-matthew/mcp-mealie). 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 →