# create_card

Create a single-use virtual card for a purchase. Use guard:true for autonomous purchases (15-min expiry).

Agent View of the PolicyLayer registry record for `create_card`. HTML page: https://policylayer.com/tools/agentpay/create-card

## Facts

- Tool: `create_card`
- Server: Agentpay (`agentpay-mcp-server`) — https://policylayer.com/tools/agentpay.md
- Install: `npx -y agentpay-mcp-server`
- Homepage: git+https://github.com/sagebhardt/agentpay.git
- Risk category: Financial (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 5 (2 required)
- Recommended policy verdict: Approval-gated

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `guard` | boolean | no | Spending guard: 15-min expiry, velocity limited |
| `amount` | number | yes | Amount in currency units (e.g. 25.00) |
| `context` | string | no | Why you need this card (shown in approval notification) |
| `currency` | string | yes | Currency code (usd, clp, brl, mxn) |
| `merchant_lock` | string | no | Restrict to this merchant |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_card",
    "arguments": {
      "amount": 0,
      "currency": "<currency>"
    }
  }
}
```

## Why create_card is rated Critical

This tool creates a virtual payment card for making purchases, directly committing financial resources. Misuse by an AI agent could result in unauthorized financial transactions. The 'autonomous purchases' feature makes this especially high-risk as it enables unsupervised spending.

From the tool's own definition: "Create a single-use virtual card for a purchase... autonomous purchases (15-min expiry)"

## Use case

AI agents use create_card to commit financial operations through Agentpay, usually the final step of a payment, billing, or trading workflow. A call moves real money.

## Recommended policy (PolicyLayer)

Verdict: **Approval-gated**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agentpay:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_card": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}
```

## Other tools on Agentpay (16)

- `close_card` — Destructive — https://policylayer.com/tools/agentpay/close-card.md
- `revoke_api_key` — Destructive — https://policylayer.com/tools/agentpay/revoke-api-key.md
- `fill_card` — Execute — https://policylayer.com/tools/agentpay/fill-card.md
- `pay_checkout` — Financial — https://policylayer.com/tools/agentpay/pay-checkout.md
- `pay_merchant_clp` — Financial — https://policylayer.com/tools/agentpay/pay-merchant-clp.md
- `pay_person_clp` — Financial — https://policylayer.com/tools/agentpay/pay-person-clp.md
- `check_account` — Read — https://policylayer.com/tools/agentpay/check-account.md
- `check_balance` — Read — https://policylayer.com/tools/agentpay/check-balance.md
- `detect_checkout` — Read — https://policylayer.com/tools/agentpay/detect-checkout.md
- `get_card_details` — Read — https://policylayer.com/tools/agentpay/get-card-details.md
- `list_api_keys` — Read — https://policylayer.com/tools/agentpay/list-api-keys.md
- `list_recipients` — Read — https://policylayer.com/tools/agentpay/list-recipients.md
- `list_transactions` — Read — https://policylayer.com/tools/agentpay/list-transactions.md
- `agentpay_signup` — Write — https://policylayer.com/tools/agentpay/agentpay-signup.md
- `create_api_key` — Write — https://policylayer.com/tools/agentpay/create-api-key.md
- `save_recipient` — Write — https://policylayer.com/tools/agentpay/save-recipient.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agentpay · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agentpay