AI agents call get_frequent_items to retrieve information from Rohlik without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
top_items | number | — | Number of top items to return overall (3-30, default: 10) |
show_categories | boolean | — | Whether to show per-category breakdown (default: true) |
top_per_category | number | — | Number of top items to show per category (1-20, default: 10) |
orders_to_analyze | number | — | Number of recent orders to analyze (1-20, default: 5) |
Parameters from the server's own tool schema.
This tool queries existing order history data to identify patterns in past purchases. It performs read-only analysis with no destructive, write, or execution capabilities. The action is informational only, returning derived insights from historical data. Severity is low because misuse would only expose personal shopping preferences, not enable financial transactions, data deletion, or external operations.
From the tool's definition Tool name: 'get_frequent_items'; description: 'Analyze your order history to find the most frequently purchased items' — retrieves and analyzes historical purchase data without modification or side effects.
Attacks that exploit this kind of access
Analyze your order history to find the most frequently purchased items. It is categorised as a Read tool in the Rohlik MCP Server, which means it retrieves data without modifying state.
get_frequent_items accepts 4 parameters: top_items, show_categories, top_per_category, orders_to_analyze. The full parameter table on this page comes from the server's own tool schema.
Register the Rohlik MCP server in PolicyLayer and add a rule for get_frequent_items: 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 Rohlik. Nothing to install.
get_frequent_items 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_frequent_items 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_frequent_items. 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_frequent_items is provided by the Rohlik MCP server (@tomaspavlin/rohlik-mcp). 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 →