AI agents call basketeer_search 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 in response to search queries. It returns data (SKU, title, price, offers) without altering state. The server description confirms catalogue tools need no auth and pose minimal risk. Misuse would only expose search patterns, not commit any financial or destructive action.
From the tool's definition Tool name 'basketeer_search' and description 'Search the Tesco grocery catalogue. Returns matching products with SKU, title, price, and any offers.' — performs a read-only query operation with no side effects. No data is created, modified, or deleted.
Attacks that exploit this kind of access
Search the Tesco grocery catalogue. Returns matching products with SKU, title, price, and any offers. 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_search: 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_search 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_search 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_search. 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_search 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 →