Obtenir les détails d
AI agents call get_product_details 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 product data from Carrefour Drive without creating, modifying, deleting, or executing operations. It is a read-only query operation similar to 'search_products' mentioned in the sibling tools. The incomplete French description ('Obtenir les détails d...') appears to mean 'Get the details' which further supports a read operation.
From the tool's definition Tool name 'get_product_details' and context indicates retrieval of product information (details, prices, nutriscore, availability). Described as part of product search functionality with no modification or deletion capability.
Attacks that exploit this kind of access
Obtenir les détails d. 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 get_product_details: 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.
get_product_details 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 get_product_details 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 get_product_details. 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.
get_product_details 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 →