stripe_raw_request · Stripe Fraud MCP: Risk & Policy

WHAT IT DOES

What stripe_raw_request does on Stripe Fraud MCP

AI agents use stripe_raw_request to commit financial operations through Stripe Fraud MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why stripe_raw_request needs a policy

This tool provides unrestricted access to all Stripe API endpoints, meaning an AI agent could use it to initiate payments, create charges, issue refunds, modify billing, cancel subscriptions, or perform any other financial operation. The server description explicitly mentions 'access any Stripe API endpoint' and 'full Stripe API access'.

From the tool's definition Direct access to any Stripe REST endpoint using the authenticated SDK client

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stripe_raw_request Approval-gated

Any call to stripe_raw_request is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

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

GATE THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Stripe Fraud MCP, so you can run agents against it safely.

FAQ

Questions about stripe_raw_request

What does the stripe_raw_request tool do? +

Direct access to any Stripe REST endpoint using the authenticated SDK client. It is categorised as a Financial tool in the Stripe Fraud MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on stripe_raw_request? +

Register the Stripe Fraud MCP server in PolicyLayer and add a rule for stripe_raw_request: 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 Stripe Fraud MCP. Nothing to install.

What risk level is stripe_raw_request? +

stripe_raw_request 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 stripe_raw_request? +

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

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

stripe_raw_request is provided by the Stripe Fraud MCP server (keithah/stripe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.