run_shopifyql · AdminAgent MCP: Risk & Policy

WHAT IT DOES

What run_shopifyql does on AdminAgent

AI agents invoke run_shopifyql to trigger actions in AdminAgent. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_shopifyql needs a policy

ShopifyQL is Shopify's query language for analytics and reporting. While primarily a Read operation (querying data), the 'run' verb and execution context on an admin system with full store access elevates this to Execute. Misuse could extract sensitive business data (customer info, revenue patterns, product secrets) or potentially modify state depending on ShopifyQL's actual capabilities in this integration.

From the tool's definition Tool name 'run_shopifyql' indicates execution of ShopifyQL queries against a Shopify store database. The server context (AdminAgent with Shopify Admin access) and sibling tools (product management, order cancellation, inventory adjustment) confirm this tool…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_shopifyql Rate-limited

run_shopifyql stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_shopifyql": {
      "limits": [
        {
          "counter": "run_shopifyql_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 run_shopifyql

What does the run_shopifyql tool do? +

run_shopifyql. It is categorised as a Execute tool in the AdminAgent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_shopifyql? +

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

run_shopifyql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_shopifyql? +

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

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

run_shopifyql 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.