AI agents use basketeer_basket_set to create or update resources in Basketeer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Basketeer environment.
This tool modifies the state of the user's shopping basket (a reversible Write operation). It does not execute arbitrary code or delete data irreversibly, distinguishing it from Execute or Destructive categories. While it could lead to unintended purchases if misused, the server's requirement for two-step confirmation on destructive actions (and likely similar safeguards on checkout) provides some protection.
From the tool's definition The tool performs a basket_set action on a SKU (stock keeping unit), which creates or modifies the shopping basket contents. The description 'Set a SKU' indicates it adds or updates items in the user's basket without permanently deleting data.
Attacks that exploit this kind of access
Set a SKU. It is categorised as a Write tool in the Basketeer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Basketeer MCP server in PolicyLayer and add a rule for basketeer_basket_set: 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_basket_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the basketeer_basket_set 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_basket_set. 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_basket_set 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 →