select_store · Mcp Starbucks MCP: Risk & Policy

WHAT IT DOES

What select_store does on Mcp Starbucks

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

WHY IT NEEDS A POLICY

Why select_store needs a policy

This tool creates or modifies session/order data by recording a store selection, which is a reversible write operation. It is not Read (does not merely query stores, as evidenced by get_nearby_stores being a separate tool), not Execute (does not run code or trigger external processes—it sets a parameter), not Destructive (the selection is reversible and can be changed), not Financial (does not move money or create…

From the tool's definition Tool performs a persistent state selection operation ('Select the Starbucks store') that modifies the user's session or order context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

select_store Rate-limited

select_store 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": {
    "select_store": {
      "limits": [
        {
          "counter": "select_store_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 Mcp Starbucks, so you can run agents against it safely.

FAQ

Questions about select_store

What does the select_store tool do? +

Select the Starbucks store for mobile pickup. Must be called before placing an order. It is categorised as a Write tool in the Mcp Starbucks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on select_store? +

Register the Mcp Starbucks MCP server in PolicyLayer and add a rule for select_store: 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 Mcp Starbucks. Nothing to install.

What risk level is select_store? +

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

Can I rate-limit select_store? +

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

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

select_store is provided by the Mcp Starbucks MCP server (markswendsen-code/mcp-starbucks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.