Add items to cart (order form)
AI agents use vtex_add_item_to_cart to create or update resources in MCP VTEX Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP VTEX Server environment.
Adding items to a shopping cart modifies order form state reversibly—it creates a cart entry that can be undone by removing items. This is a Write operation (not Execute, as it doesn't run arbitrary code; not Destructive, as it's reversible; not Financial, as it doesn't commit payment).
From the tool's definition Tool name 'vtex_add_item_to_cart' and description 'Add items to cart (order form)' indicate creation/modification of cart data, which is reversible (items can be removed).
Attacks that exploit this kind of access
Add items to cart (order form). It is categorised as a Write tool in the MCP VTEX Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP VTEX Server MCP server in PolicyLayer and add a rule for vtex_add_item_to_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 VTEX Server. Nothing to install.
vtex_add_item_to_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 vtex_add_item_to_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 vtex_add_item_to_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.
vtex_add_item_to_cart is provided by the MCP VTEX Server MCP server (leosepulveda/mcp-vtex). 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 →