Medium Risk

fill_card

Fill only the card fields on a checkout page with an existing card. Use when you already have a card ID and want to handle the rest yourself. The card number is sent directly to the browser — you never see it.

Part of the Agentpay server.

fill_card can modify Agentpay data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE AGENTPAY →

Free to start. No card required.

AI agents use fill_card to create or modify resources in Agentpay. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call fill_card repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agentpay.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "fill_card": {
      "limits": [
        {
          "counter": "fill_card_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Agentpay policy for all 17 tools.

Get this rule live on your own Agentpay server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY AGENTPAY →

View all 17 tools →

These attack patterns abuse exactly the kind of access fill_card gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so fill_card only ever does what you allow.

SECURE AGENTPAY →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the fill_card tool do? +

Fill only the card fields on a checkout page with an existing card. Use when you already have a card ID and want to handle the rest yourself. The card number is sent directly to the browser — you never see it.. It is categorised as a Write tool in the Agentpay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on fill_card? +

Register the Agentpay MCP server in PolicyLayer and add a rule for fill_card: 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 fill_card? +

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

Can I rate-limit fill_card? +

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

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

fill_card 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.

Enforce policy on every Agentpay tool call.

Deterministic rules across all 17 Agentpay tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.