Close a return (mark as resolved).
AI agents use close_return 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.
This tool modifies the status of a return record, making it a Write operation rather than Read (queries only) or Destructive (permanent deletion). However, severity is high because returns are critical to customer satisfaction and financial reconciliation; closing a return incorrectly could block legitimate refunds or create accounting discrepancies.
From the tool's definition Tool name 'close_return' and description 'mark as resolved' indicate modification of return record status from open to closed state. This is a reversible state change operation on existing data.
Attacks that exploit this kind of access
Close a return (mark as resolved). 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_return: 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_return 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_return 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_return. 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_return 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 →