detect_checkout

Scan the active browser tab for a payment form. Returns which fields were found (card number, CVV, expiry, name). Requires the AgentPay Chrome extension.

SERVERAgentpay SOURCEagentpay-mcp-server

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/agentpay/detect-checkout.md

WHAT IT DOES

What detect_checkout does on Agentpay

AI agents call detect_checkout to retrieve information from Agentpay without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why detect_checkout is rated Low

This tool retrieves and queries data (detecting form field presence) without side effects or irreversible actions. While it operates in a payment context, it performs passive observation only—scanning a webpage for field information. It does not execute transactions, modify payment systems, or destroy data.

From the tool's definition Tool 'detect_checkout' scans and returns information about payment form fields present on the active browser tab. The description explicitly states it 'Returns which fields were found' with no mention of modifying, executing actions on, or deleting data.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs detect_checkout safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Agentpay, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For detect_checkout, this is the rule to start with:

detect_checkout Allowed

detect_checkout is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "detect_checkout": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Agentpay, apply this rule, and every detect_checkout call is checked against it from then on.

FAQ

Questions about detect_checkout

What does the detect_checkout tool do? +

Scan the active browser tab for a payment form. Returns which fields were found (card number, CVV, expiry, name). Requires the AgentPay Chrome extension. It is categorised as a Read tool in the Agentpay MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on detect_checkout? +

Register the Agentpay MCP server in PolicyLayer and add a rule for detect_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 Agentpay. Nothing to install.

What risk level is detect_checkout? +

detect_checkout is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit detect_checkout? +

Yes. Add a rate_limit block to the detect_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 detect_checkout completely? +

Set action: deny in the PolicyLayer policy for detect_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 detect_checkout? +

detect_checkout is provided by the Agentpay MCP server (agentpay-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agentpay, and thousands of servers like it.

This server

All 17 Agentpay tools →

Across the catalogue

detect_slop on Slop Cop → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →