Cancel all open orders, optionally filtered by asset.
AI agents call cancel_all_orders to permanently remove resources in Hyperliquid — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling all open orders is an irreversible action that removes active trading positions/intentions en masse. Unlike cancelling a single order, this bulk operation cannot be undone and could have significant financial impact (e.g., leaving positions unhedged, missing fills). It falls under Destructive due to its irreversible, bulk nature, though it also has Financial implications.
From the tool's definition 'Cancel all open orders' — cancels all open orders, optionally filtered by asset
Attacks that exploit this kind of access
Cancel all open orders, optionally filtered by asset. It is categorised as a Destructive tool in the Hyperliquid MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hyperliquid 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 Hyperliquid. 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 Hyperliquid MCP server (midodimori/hyperliquid-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 →