Close/archive an order.
AI agents use close_order to create or update resources in AdminAgent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdminAgent environment.
Closing/archiving an order changes its state and visibility in the system but does not delete data or prevent undo. This is a state modification (Write) rather than Destructive. However, severity is high because misuse could disrupt order management workflows, reconciliation processes, and customer service operations for an entire store.
From the tool's definition Tool description states 'Close/archive an order' — this modifies order state from active to closed/archived, which is reversible (orders can be reopened or unarchived in most e-commerce systems).
Attacks that exploit this kind of access
Close/archive an order. It is categorised as a Write tool in the AdminAgent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AdminAgent MCP server in PolicyLayer and add a rule for close_order: 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 AdminAgent. Nothing to install.
close_order is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the close_order 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 close_order. 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.
close_order is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →