Voir le contenu actuel du panier de courses avec le total.
AI agents call view_cart to retrieve information from Mcp Carrefour without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing cart information—a read-only query operation. It has no side effects, creates no data changes, and poses minimal risk even if called by an AI agent. The operation is consistent with the 'Read' category for data retrieval tools.
From the tool's definition Tool name 'view_cart' and description 'Voir le contenu actuel du panier de courses avec le total' (View the current shopping cart contents with the total) indicate retrieval of cart data with no modification capability.
Attacks that exploit this kind of access
Voir le contenu actuel du panier de courses avec le total. It is categorised as a Read tool in the Mcp Carrefour MCP Server, which means it retrieves data without modifying state.
Register the Mcp Carrefour MCP server in PolicyLayer and add a rule for view_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.
view_cart is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the view_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 view_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.
view_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 →