AI agents call basketeer_product to retrieve information from Basketeer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves product information from the Tesco catalogue by SKU. It performs a GET-like operation that does not modify state, create orders, delete data, or execute arbitrary code. The server description notes that 'catalogue + nutrition tools need no auth' and do not require confirmation, confirming they are safe read operations. No destructive, financial, or code-execution risk is present.
From the tool's definition Tool description states 'Fetch one product by SKU (tpnc), including price, pack size, promotions, and nutrition.' The verb 'fetch' and the data returned (price, pack size, promotions, nutrition) indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Fetch one product by SKU (tpnc), including price, pack size, promotions, and nutrition. It is categorised as a Read tool in the Basketeer MCP Server, which means it retrieves data without modifying state.
Register the Basketeer MCP server in PolicyLayer and add a rule for basketeer_product: 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 Basketeer. Nothing to install.
basketeer_product 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 basketeer_product 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 basketeer_product. 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.
basketeer_product is provided by the Basketeer MCP server (tobyandrews1985/basketeer). 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 →