Delete a recipe from a project
AI agents call delete_recipe to permanently remove resources in Dataiku DSS MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a recipe is a destructive operation that cannot be undone without restoration from backups. A recipe in Dataiku DSS is a data transformation workflow; its removal eliminates the logic and configuration permanently. This poses significant risk if invoked incorrectly by an AI agent, as it could disrupt data pipelines and workflows that depend on the recipe.
From the tool's definition Tool name is 'delete_recipe' with description 'Delete a recipe from a project'. The verb 'delete' is explicit and unambiguous—this operation irreversibly removes a recipe artifact.
Attacks that exploit this kind of access
Delete a recipe from a project. It is categorised as a Destructive tool in the Dataiku DSS MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dataiku DSS MCP Server MCP server in PolicyLayer and add a rule for delete_recipe: 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 Dataiku DSS MCP Server. Nothing to install.
delete_recipe 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_recipe 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_recipe. 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_recipe is provided by the Dataiku DSS MCP Server MCP server (steven0lisa/mcp-dataiku). 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 →