Remove every item from the shop's online cart for the authenticated user.
AI agents call clear_cart to permanently remove resources in Cz Mtg Compare — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing an entire cart removes all items at once and is not easily reversible without knowing what was previously in the cart. The blast radius is high because a misuse could wipe out a carefully assembled order, requiring the user to manually re-add all items. This is an irreversible bulk-delete operation on user data.
From the tool's definition Remove every item from the shop's online cart for the authenticated user
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Remove every item from the shop's online cart for the authenticated user. It is categorised as a Destructive tool in the Cz Mtg Compare MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cz Mtg Compare MCP server in PolicyLayer and add a rule for clear_cart: 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 Cz Mtg Compare. Nothing to install.
clear_cart 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 clear_cart 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 clear_cart. 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.
clear_cart is provided by the Cz Mtg Compare MCP server (xvyslo05/czech-mtg-price-comparator-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 →