Meal Planning: Delete a menu item
AI agents call delete_menu_item to permanently remove resources in Saffron MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes data (a menu item) without the ability to undo or recover it. While the impact is scoped to a single menu planning entry rather than a full database, deletion is inherently destructive and cannot be reversed. The high severity reflects that an AI agent could accidentally remove meal plans or menu entries that users depend on, requiring manual restoration or re-entry.
From the tool's definition Tool name contains 'delete' and description states 'Delete a menu item' — this is an irreversible deletion operation.
Attacks that exploit this kind of access
Meal Planning: Delete a menu item. It is categorised as a Destructive tool in the Saffron MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Saffron MCP Server MCP server in PolicyLayer and add a rule for delete_menu_item: 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 Saffron MCP Server. Nothing to install.
delete_menu_item 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_menu_item 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_menu_item. 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_menu_item is provided by the Saffron MCP Server MCP server (tvh/saffron-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 →