Withdraw funds to external wallet.
AI agents use withdraw_funds to commit financial operations through Infini Payment MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves financial assets (cryptocurrency) from the Infini Payment system to external wallet addresses. Such action commits a financial obligation and transfers ownership of funds. This is a core financial operation with maximum blast radius if misused by an AI agent—funds withdrawn cannot be easily recovered.
From the tool's definition Tool is described as 'Withdraw funds to external wallet' on a cryptocurrency payment processing server supporting 'multi-chain withdrawals' of 'USDC/USDT transactions'.
Attacks that exploit this kind of access
Withdraw funds to external wallet. It is categorised as a Financial tool in the Infini Payment MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Infini Payment MCP Server MCP server in PolicyLayer and add a rule for withdraw_funds: 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 Infini Payment MCP Server. Nothing to install.
withdraw_funds 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 withdraw_funds 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 withdraw_funds. 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.
withdraw_funds is provided by the Infini Payment MCP Server MCP server (yanboishere/infini-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →