View the current items in the shopping cart.
AI agents call get_cart to retrieve information from Perkakasku without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays cart contents without any side effects. It is a simple query operation that does not create, modify, delete, or execute any actions. The minimal sensitivity of the data (user's own cart items) and lack of any capability for misuse keeps severity low.
From the tool's definition Tool name 'get_cart' and description 'View the current items in the shopping cart' indicate a read-only retrieval operation with no data modification, deletion, or external effects.
Attacks that exploit this kind of access
View the current items in the shopping cart. It is categorised as a Read tool in the Perkakasku MCP Server, which means it retrieves data without modifying state.
Register the Perkakasku MCP server in PolicyLayer and add a rule for get_cart: 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 Perkakasku. Nothing to install.
get_cart 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_cart 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_cart. 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_cart is provided by the Perkakasku MCP server (perkakasku-mcp-server). 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 →