mark_order_paid · AdminAgent MCP: Risk & Policy

WHAT IT DOES

What mark_order_paid does on AdminAgent

AI agents use mark_order_paid 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.

WHY IT NEEDS A POLICY

Why mark_order_paid needs a policy

This tool modifies order records by changing payment status, making it a Write operation rather than Financial (which would involve actual money movement like capture_payment). However, the severity is high because misuse could mark unpaid orders as paid, creating billing discrepancies and customer disputes. The confidence is high due to the clear, explicit description of the action performed.

From the tool's definition Tool explicitly does 'Mark an order as paid', which modifies order payment status. This is a state change operation on financial records but does not move money or create actual financial obligations—it updates metadata about payment receipt for 'manual…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_order_paid Rate-limited

mark_order_paid stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_order_paid": {
      "limits": [
        {
          "counter": "mark_order_paid_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches AdminAgent, so you can run agents against it safely.

FAQ

Questions about mark_order_paid

What does the mark_order_paid tool do? +

Mark an order as paid (for manual payment methods). 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.

How do I enforce a policy on mark_order_paid? +

Register the AdminAgent MCP server in PolicyLayer and add a rule for mark_order_paid: 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.

What risk level is mark_order_paid? +

mark_order_paid is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mark_order_paid? +

Yes. Add a rate_limit block to the mark_order_paid 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.

How do I block mark_order_paid completely? +

Set action: deny in the PolicyLayer policy for mark_order_paid. 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.

What MCP server provides mark_order_paid? +

mark_order_paid 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.