Delete a food/ingredient from Mealie.
AI agents call delete_food to permanently remove resources in Mealie MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes food/ingredient records from the Mealie database with no stated undo capability. Deletion is irreversible, making it Destructive rather than Write. The severity is high because deleting a food item could break meal plans, recipes, and shopping lists that reference it, causing cascading data integrity issues.
From the tool's definition Tool name is 'delete_food' and description explicitly states 'Delete a food/ingredient from Mealie.' The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a food/ingredient from Mealie. It is categorised as a Destructive tool in the Mealie MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mealie MCP Server MCP server in PolicyLayer and add a rule for delete_food: 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 Mealie MCP Server. Nothing to install.
delete_food 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_food 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_food. 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_food is provided by the Mealie MCP Server MCP server (nikopol666/mealie-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 →