Update the quantity of an item in the cart or remove it (set quantity to 0)
AI agents use update_cart to create or update resources in Mcp Drizly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Drizly environment.
This tool creates or modifies shopping cart data reversibly. While it affects a financial transaction (alcohol purchase), the actual financial commitment and money transfer occur only at place_order. The update_cart action itself is a Write operation (modifying cart state) rather than Financial (no funds move).
From the tool's definition Tool description states 'Update the quantity of an item in the cart or remove it (set quantity to 0)' — this modifies cart contents reversibly. Can add/increase items or decrease/remove them, but changes are not permanent until checkout.
Attacks that exploit this kind of access
Update the quantity of an item in the cart or remove it (set quantity to 0). It is categorised as a Write tool in the Mcp Drizly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Drizly MCP server in PolicyLayer and add a rule for update_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 Drizly. Nothing to install.
update_cart is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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 update_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.
update_cart is provided by the Mcp Drizly MCP server (markswendsen-code/mcp-drizly). 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 →