AI agents use create_withdrawal_requests to commit financial operations through Zbd — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool creates Bitcoin withdrawal requests, which directly moves or commits cryptocurrency funds. Even though it generates QR codes (vouchers), the act of creating withdrawal requests initiates a financial transaction that cannot be trivially reversed.
From the tool's definition 'create_withdrawal_requests' and 'Start creating Bitcoin voucher QR codes' — initiates Bitcoin withdrawals, committing financial obligations
Attacks that exploit this kind of access
Start creating Bitcoin voucher QR codes. It is categorised as a Financial tool in the Zbd MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Zbd MCP server in PolicyLayer and add a rule for create_withdrawal_requests: 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 Zbd. Nothing to install.
create_withdrawal_requests is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the create_withdrawal_requests 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.
Set action: deny in the PolicyLayer policy for create_withdrawal_requests. 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.
create_withdrawal_requests is provided by the Zbd MCP server (zebedeeio/zbd-payments-typescript-sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
create_withdrawal_requests is one line of Zbd's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →