Retirer un produit du panier.
AI agents use remove_from_cart to create or update resources in Mcp Carrefour — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Carrefour environment.
Removing an item from a shopping cart is a reversible write operation — the item can be re-added. It modifies state (the cart) but does not commit any financial transaction, delete data permanently, or execute code. Severity is medium because misuse could disrupt a user's shopping session, but the action is easily undone.
From the tool's definition 'Retirer un produit du panier' (Remove a product from the cart)
Attacks that exploit this kind of access
Retirer un produit du panier. It is categorised as a Write tool in the Mcp Carrefour MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Carrefour MCP server in PolicyLayer and add a rule for remove_from_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 Carrefour. Nothing to install.
remove_from_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 remove_from_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 remove_from_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.
remove_from_cart is provided by the Mcp Carrefour MCP server (nicovlr/mcp-carrefour). 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 →