取消單筆掛單
AI agents call cancel_order to permanently remove resources in MAX Exchange MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling an order is an irreversible action — once a standing order is cancelled it cannot be reinstated. In a trading context, this can cause financial loss if an AI agent cancels orders at the wrong time, making it at minimum Destructive. While it doesn't move money directly, the irreversible cancellation of a financial instrument order warrants high severity.
From the tool's definition cancel_order / 取消單筆掛單 (cancel a single pending order)
Attacks that exploit this kind of access
取消單筆掛單. It is categorised as a Destructive tool in the MAX Exchange MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MAX Exchange MCP Server MCP server in PolicyLayer and add a rule for cancel_order: 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 MAX Exchange MCP Server. Nothing to install.
cancel_order is a Destructive 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 cancel_order 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 cancel_order. 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.
cancel_order is provided by the MAX Exchange MCP Server MCP server (nicky512500/max-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 →