Submit a withdrawal.
AI agents use withdraw to commit financial operations through Mcp Kraken — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money (cryptocurrency) out of a user's exchange account to an external address. Even a single misuse by an AI agent could result in irreversible loss of funds. Withdrawals are financial transactions with direct monetary impact, making this critical severity.
From the tool's definition Tool name 'withdraw' on a cryptocurrency exchange server (mcp-kraken) described as enabling 'trading' and 'account management' through the Kraken Spot REST API. Withdrawal is explicitly a financial operation that moves cryptocurrency/funds out of an account.
Attacks that exploit this kind of access
Submit a withdrawal. It is categorised as a Financial tool in the Mcp Kraken MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Kraken MCP server in PolicyLayer and add a rule for withdraw: 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 Mcp Kraken. Nothing to install.
withdraw 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 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. 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 is provided by the Mcp Kraken MCP server (xavierbeheydt/mcp-kraken). 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 →