approve_return_request · Shopify Graphql MCP: Risk & Policy

WHAT IT DOES

What approve_return_request does on Shopify Graphql

AI agents use approve_return_request to create or update resources in Shopify Graphql — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shopify Graphql environment.

WHY IT NEEDS A POLICY

Why approve_return_request needs a policy

This tool creates or modifies data (approval status of a return request) in a reversible manner. It is not destructive because approval decisions can be reversed. It is not Execute because it doesn't run arbitrary code or trigger unpredictable external operations—it performs a specific business operation. It is not Financial despite touching returns, as it only changes approval status, not monetary transfers.

From the tool's definition Tool description states 'Approve a return request' which modifies the status of a return request from pending to approved. This changes data state in the Shopify system reversibly (returns can be unapproved or cancelled).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_return_request Rate-limited

approve_return_request 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": {
    "approve_return_request": {
      "limits": [
        {
          "counter": "approve_return_request_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 Shopify Graphql, so you can run agents against it safely.

FAQ

Questions about approve_return_request

What does the approve_return_request tool do? +

Approve a return request. It is categorised as a Write tool in the Shopify Graphql MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_return_request? +

Register the Shopify Graphql MCP server in PolicyLayer and add a rule for approve_return_request: 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 Shopify Graphql. Nothing to install.

What risk level is approve_return_request? +

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

Can I rate-limit approve_return_request? +

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

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

approve_return_request is provided by the Shopify Graphql MCP server (uvu-store/shopify-graphql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.