AI agents call get_account_data 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.
This tool retrieves account data (delivery details, orders, announcements, cart contents) without creating, modifying, or deleting anything. It is a Read operation. Severity is medium because account information may include personally identifiable information (PII), delivery addresses, and order history that could be sensitive if disclosed, though the tool itself does not move money or cause irreversible harm.
From the tool's definition Tool name 'get_account_data' and description 'Get comprehensive account information including delivery details, orders, announcements, cart, and more' indicate data retrieval without modification.
Attacks that exploit this kind of access
Get comprehensive account information including delivery details, orders, announcements, cart, and more. It is categorised as a Read tool in the Rohlik MCP Server, which means it retrieves data without modifying state.
Register the Rohlik MCP server in PolicyLayer and add a rule for get_account_data: 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_account_data 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_account_data 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_account_data. 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_account_data 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 →