Delete a recipe from your cookbook.
AI agents call recipe_delete to permanently remove resources in Old Family Recipe — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is irreversible and destroys user data (a recipe). Even though the blast radius is limited to a single recipe rather than the entire database, and recipes can theoretically be re-imported or re-created, the action itself is destructive. This falls into the Destructive category rather than Write because the operation cannot be undone through normal means (no undo, no soft-delete mentioned).
From the tool's definition Tool name is 'recipe_delete' and description states 'Delete a recipe from your cookbook' — this permanently removes data with no reversal mechanism mentioned.
Attacks that exploit this kind of access
Delete a recipe from your cookbook. It is categorised as a Destructive tool in the Old Family Recipe MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Old Family Recipe MCP server in PolicyLayer and add a rule for recipe_delete: 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 Old Family Recipe. Nothing to install.
recipe_delete 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 recipe_delete 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 recipe_delete. 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.
recipe_delete is provided by the Old Family Recipe MCP server (oldfamilyrecipe/ai). 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 →