ARC · DEVELOPERS · MCP TOOLS · CHECK A STORE

can_agent_checkout

Can an agent check out?

Free live HTTP check of any public store: agent catalog, product found, checkout link returned, UCP profile, storefront WebMCP, Checkout WebMCP (Shopify-only checkoutWebmcp: status, detected nullable boolean, tools, reason; buyer approval required), storefront MCP, robots, product data and policies.

NO LOGINNOT READ-ONLYNOT DESTRUCTIVEIDEMPOTENTREACHES THE OPEN WEBWRITES

What it does

Can an AI agent buy from this store or check out on this Shopify store? Free real HTTP check of any public homepage or product URL: agent catalog, product, checkout link, UCP profile, Checkout WebMCP (Shopify-only checkoutWebmcp: status, nullable detected, tools, reason; buyer approval required), Shopify WebMCP storefront adapter (used by browser agents; detected in the HTML, not a browser session), blocks, and the fix. No login, model call, payment, or browser scan. Cached per host for 24 hours. A returned link means reach checkout, not a completed purchase.

Writes: A fresh check saves its result to ARC's public directory (CC-BY-4.0). No checkout URL is stored and no purchase is made.

Limits: Cached per host for 24 hours. 50 requests and 10 fresh checks per network per UTC day; 500 fresh checks site-wide.

Arguments

Name	Type	Required	Description
url	string	yes	Public store homepage or product URL

Full input JSON Schema

INPUT SCHEMA

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public store homepage or product URL"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Call it

From Claude, Cursor, ChatGPT or VS Code, connect the server (config) and ask in plain words; the client picks the tool. Or call it directly with JSON-RPC:

CURL · JSON-RPC

curl -s https://www.arcreport.ai/api/ask \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"can_agent_checkout","arguments":{"url":"allbirds.com"}}}'

JAVASCRIPT

const res = await fetch("https://www.arcreport.ai/api/ask", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "can_agent_checkout",
      "arguments": {
        "url": "allbirds.com"
      }
    }
  }),
});
const { result } = await res.json();
const data = JSON.parse(result.content[0].text); // result.isError is true on errors
console.log(data);

PYTHON

import json, requests

res = requests.post("https://www.arcreport.ai/api/ask", json={
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "can_agent_checkout",
        "arguments": {
            "url": "allbirds.com"
        }
    }
}, timeout=30)
result = res.json()["result"]
print(json.loads(result["content"][0]["text"]))

REST equivalent

GET /api/agent-checkout. Documented in openapi.json.

CURL · GET

curl -s 'https://www.arcreport.ai/api/agent-checkout?url=allbirds.com'