AI agents call order_get to retrieve information from Voog 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 by ID without modifying, deleting, or executing operations. It is a straightforward query operation with no side effects. While order data may be sensitive (e.g., customer information, payment details), the tool itself performs only read access. Severity is low because retrieval alone does not alter state or enable direct harmful actions; the risk depends on downstream use of the data.
From the tool's definition Tool name 'order_get' and description 'Get a single order by id (GET /admin/api/ecommerce/v1/' indicate a retrieval operation using HTTP GET method. The verb 'Get' and HTTP GET clearly signal read-only access.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get a single order by id (GET /admin/api/ecommerce/v1/. It is categorised as a Read tool in the Voog MCP Server, which means it retrieves data without modifying state.
Register the Voog MCP server in PolicyLayer and add a rule for order_get: 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 Voog. Nothing to install.
order_get 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 order_get 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 order_get. 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.
order_get is provided by the Voog MCP server (runnel/voog-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 →