getRecentOrders
AI agents call getRecentOrders to retrieve information from Woocommerce without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves order data from a WooCommerce store without modifying, deleting, or executing actions. While the data retrieved may be sensitive (customer orders contain PII and financial details), the tool itself performs only a read query. Severity is medium because exposure of historical order data could leak customer information, but the tool has no destructive or financial capability itself.
From the tool's definition Tool name 'getRecentOrders' and server description 'fetching recent orders with optional filtering' indicate data retrieval with no side effects. The tool description is empty, but sibling context and naming strongly suggest a read operation.
Attacks that exploit this kind of access
getRecentOrders. It is categorised as a Read tool in the Woocommerce MCP Server, which means it retrieves data without modifying state.
Register the Woocommerce MCP server in PolicyLayer and add a rule for getRecentOrders: 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 Woocommerce. Nothing to install.
getRecentOrders 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 getRecentOrders 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 getRecentOrders. 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.
getRecentOrders is provided by the Woocommerce MCP server (opestro/woocommerce-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 →