AI agents call basketeer_search_by_nutrition 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 and queries product information filtered by nutritional properties. It has no side effects—it does not create, modify, delete, or execute any operations. The search and ranking operations are purely informational read operations against a product catalogue.
From the tool's definition Tool description states 'Search products by keyword, then filter/rank by nutrition' with no modification of data. Server description confirms 'Catalogue + nutrition tools need no auth' and are not destructive actions.
Attacks that exploit this kind of access
Search products by keyword, then filter/rank by nutrition (per 100g/ml). 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_by_nutrition: 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_by_nutrition 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_by_nutrition 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_by_nutrition. 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_by_nutrition 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 →