basketeer_checkout · Basketeer MCP: Risk & Policy

WHAT IT DOES

What basketeer_checkout does on Basketeer

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

WHY IT NEEDS A POLICY

Why basketeer_checkout needs a policy

This tool transitions a shopping basket into a checkout state, creating a financial commitment pathway. While the human completes the actual payment (mitigating severity), the tool itself commits the basket contents and initiates the financial workflow. It is Write rather than Financial because payment execution happens outside the tool's control via human browser interaction.

From the tool's definition Tool returns 'the current basket and the URL where a HUMAN completes payment'; initiates a checkout workflow that modifies the transaction state and prepares payment, though actual payment execution is deferred to human browser interaction.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

basketeer_checkout Rate-limited

basketeer_checkout 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": {
    "basketeer_checkout": {
      "limits": [
        {
          "counter": "basketeer_checkout_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 Basketeer, so you can run agents against it safely.

FAQ

Questions about basketeer_checkout

What does the basketeer_checkout tool do? +

Prepare checkout: returns the current basket and the URL where a HUMAN completes payment in a browser. It is categorised as a Write tool in the Basketeer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on basketeer_checkout? +

Register the Basketeer MCP server in PolicyLayer and add a rule for basketeer_checkout: 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 Basketeer. Nothing to install.

What risk level is basketeer_checkout? +

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

Can I rate-limit basketeer_checkout? +

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

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

basketeer_checkout is provided by the Basketeer MCP server (tobyandrews1985/basketeer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.