Remove a SKU from the basket entirely.
AI agents call basketeer_basket_remove to permanently remove resources in Basketeer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool removes an item from the basket entirely, which is an irreversible action within the session context — the item is gone from the basket with no undo step described. While the server description mentions a two-step confirm for destructive actions, the action itself is destructive (permanent removal). Severity is medium since it affects basket contents rather than orders or financial transactions.
From the tool's definition Remove a SKU from the basket entirely.
Attacks that exploit this kind of access
Remove a SKU from the basket entirely. It is categorised as a Destructive tool in the Basketeer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Basketeer MCP server in PolicyLayer and add a rule for basketeer_basket_remove: 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 Basketeer. Nothing to install.
basketeer_basket_remove 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 basketeer_basket_remove 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 basketeer_basket_remove. 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.
basketeer_basket_remove is provided by the Basketeer MCP server (tobyandrews1985/basketeer). 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 →