AI agents call picnic_clear_cart to permanently remove resources in MCP Picnic — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cart removes all items at once with no indication of reversibility. While it doesn't delete permanent data (orders, account info), it destroys the user's carefully curated cart contents in a single action. This is analogous to a bulk delete operation, making it Destructive. Severity is high because an AI agent misusing this tool could wipe a large grocery order without recovery.
From the tool's definition 'Clear all items from the shopping cart' — removes all cart contents irreversibly
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access picnic_clear_cart gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Picnic, and nothing reaches the server without passing your rules. This is the rule we recommend for picnic_clear_cart:
{
"version": "1",
"default": "deny",
"hide": [
"picnic_clear_cart"
]
} picnic_clear_cart disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Clear all items from the shopping cart. It is categorised as a Destructive tool in the MCP Picnic MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Picnic MCP server in PolicyLayer and add a rule for picnic_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 MCP Picnic. Nothing to install.
picnic_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 picnic_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 picnic_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.
picnic_clear_cart is provided by the MCP Picnic MCP server (ivo-toby/mcp-picnic). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Picnic, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 MCP Picnic tools catalogued and risk-classified — across an index of 43,000+ MCP servers.