Cancel all open orders.
AI agents call cancel_all_orders to permanently remove resources in Ib Async — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Canceling all open orders is a destructive action that cannot be easily undone and has immediate financial consequences. An AI agent invoking this without explicit user confirmation could liquidate a complex multi-leg trading strategy in seconds, causing substantial losses. This represents the highest severity destructive action available on a financial trading platform.
From the tool's definition Tool name is 'cancel_all_orders' and description states it will 'Cancel all open orders.' This irreversibly terminates all pending trades without individual selection.
Attacks that exploit this kind of access
Cancel all open orders. It is categorised as a Destructive tool in the Ib Async MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ib Async MCP server in PolicyLayer and add a rule for cancel_all_orders: 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 Ib Async. Nothing to install.
cancel_all_orders 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_all_orders 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_all_orders. 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_all_orders is provided by the Ib Async MCP server (nadavgb-atom/ib-async-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 →