Fetch the user
AI agents call mcp__willys_get_orders to retrieve information from Willys MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves order history or order data for the authenticated user. It performs a read-only operation with no side effects. Severity is medium rather than low because orders may contain sensitive personal and financial information (items purchased, addresses, payment methods, order totals), making unauthorized or careless access a privacy/security concern.
From the tool's definition Tool name contains 'get_orders' and description states 'Fetch the user' (likely incomplete, should be 'fetch the user's orders'). The 'get' verb and 'fetch' action indicate data retrieval without modification.
Attacks that exploit this kind of access
Fetch the user. It is categorised as a Read tool in the Willys MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Willys MCP Server MCP server in PolicyLayer and add a rule for mcp__willys_get_orders: 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 Willys MCP Server. Nothing to install.
mcp__willys_get_orders 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 mcp__willys_get_orders 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 mcp__willys_get_orders. 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.
mcp__willys_get_orders is provided by the Willys MCP Server MCP server (jimmystridh/willys-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 →