recipe_delete
Use this when the user wants to remove one of THEIR saved recipes/skills (the manifests under ~/.local/share/local-mcp/recipes). Destructive with a preview gate: the first call (without confirm) shows what would be deleted; call again with confirm=true to actually delete. Bundled starter recipes ...
This record as markdown: /tools/com-local-mcp-local-mcp/recipe-delete.md
What recipe_delete does on Local
AI agents call recipe_delete to permanently remove resources in Local, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Recipe name (from recipe_list). |
confirm | boolean | — | Must be true to actually delete. Without it, returns a preview. |
Parameters from the server's own tool schema.
Why recipe_delete is rated Critical
This tool permanently deletes user data (recipe manifests) without recovery possibility. Although it includes a preview/confirmation gate to reduce accidental misuse, the core action is irreversible deletion of user-owned files. This fits the Destructive category (delete, drop, purge operations that cannot be undone).
From the tool's definition Tool explicitly described as 'Destructive with a preview gate' that 'remove[s]' saved recipes. The mechanism involves irreversibly deleting user-created recipe manifests from ~/.local/share/local-mcp/recipes.
Attacks that exploit this kind of access
The rule that runs recipe_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For recipe_delete, this is the rule to start with:
recipe_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every recipe_delete call is checked against it from then on.
Questions about recipe_delete
Use this when the user wants to remove one of THEIR saved recipes/skills (the manifests under ~/.local/share/local-mcp/recipes). Destructive with a preview gate: the first call (without confirm) shows what would be deleted; call again with confirm=true to actually delete. Bundled starter recipes can't be deleted. To modify a recipe instead, recipe_save with the same name overwrites it (upsert). It is categorised as a Destructive tool in the Local MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
recipe_delete accepts 2 parameters: name, confirm. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Local 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 Local. 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 Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue