send_draft_invoice · AdminAgent MCP: Risk & Policy

WHAT IT DOES

What send_draft_invoice does on AdminAgent

AI agents use send_draft_invoice 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 send_draft_invoice needs a policy

Sending a draft invoice modifies store state by creating or dispatching an invoice record to a customer, which is reversible (invoices can be voided or replaced). This is a Write operation rather than Destructive (no permanent deletion) or Financial (no direct money movement, though it may trigger payment).

From the tool's definition Tool name 'send_draft_invoice' and context of Shopify Admin operations indicate this creates or sends an invoice document.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_draft_invoice Rate-limited

send_draft_invoice 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": {
    "send_draft_invoice": {
      "limits": [
        {
          "counter": "send_draft_invoice_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 send_draft_invoice

What does the send_draft_invoice tool do? +

send_draft_invoice. 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 send_draft_invoice? +

Register the AdminAgent MCP server in PolicyLayer and add a rule for send_draft_invoice: 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 send_draft_invoice? +

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

Can I rate-limit send_draft_invoice? +

Yes. Add a rate_limit block to the send_draft_invoice 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 send_draft_invoice completely? +

Set action: deny in the PolicyLayer policy for send_draft_invoice. 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 send_draft_invoice? +

send_draft_invoice 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.