Critical Risk →

request_refund

Request a refund for a previous order. Refund policy: (1) within 7 days of purchase, (2) no annotation posted on the book, (3) downloaded ≤1 time, (4) ≤3 refunds in the last 30 days. Refunding revokes the entitlement and invalidates new download tokens, but any local copy the buyer already downlo...

Part of the Bookstore4agents server.

request_refund can move real money through Bookstore4agents, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE BOOKSTORE4AGENTS →

Free to start. No card required.

AI agents use request_refund to initiate financial transactions through Bookstore4agents. Financial operations involve real money and are irreversible once processed. PolicyLayer blocks financial tools by default, requiring explicit human approval with transaction-level limits to prevent unauthorised spending.

request_refund moves real money. Without a policy, an autonomous agent could initiate transactions that drain accounts or exceed budgets. PolicyLayer blocks financial tools by default, requiring human-in-the-loop approval with configurable spending limits per transaction and per time window.

Financial tools involve real money. Block by default and require explicit human approval before enabling.

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

See the full Bookstore4agents policy for all 49 tools.

Get this rule live on your own Bookstore4agents server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY BOOKSTORE4AGENTS →

View all 49 tools →

These attack patterns abuse exactly the kind of access request_refund 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 request_refund only ever does what you allow.

SECURE BOOKSTORE4AGENTS →

Other financial tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the request_refund tool do? +

Request a refund for a previous order. Refund policy: (1) within 7 days of purchase, (2) no annotation posted on the book, (3) downloaded ≤1 time, (4) ≤3 refunds in the last 30 days. Refunding revokes the entitlement and invalidates new download tokens, but any local copy the buyer already downloaded remains theirs (digital goods can't be 'returned').. It is categorised as a Financial tool in the Bookstore4agents MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on request_refund? +

Register the Bookstore4agents MCP server in PolicyLayer and add a rule for request_refund: 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 Bookstore4agents. Nothing to install.

What risk level is request_refund? +

request_refund is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit request_refund? +

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

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

request_refund is provided by the Bookstore4agents MCP server (https://bookstore4agents-mcp.bookstore4agents.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Bookstore4agents tool call.

Deterministic rules across all 49 Bookstore4agents 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.