EMERGENCY: Close ALL positions and cancel ALL orders immediately.
AI agents call panic_button to permanently remove resources in Asterdex — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs a blanket closure of all trading positions and cancellation of all orders. While cancellations are reversible, position closures are irreversible market transactions that lock in losses/gains and permanently terminate active trades.
From the tool's definition Tool name 'panic_button' with description 'EMERGENCY: Close ALL positions and cancel ALL orders immediately.' Explicitly closes ALL positions and cancels ALL orders in a single irreversible action without selective targeting.
Attacks that exploit this kind of access
EMERGENCY: Close ALL positions and cancel ALL orders immediately. It is categorised as a Destructive tool in the Asterdex MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Asterdex MCP server in PolicyLayer and add a rule for panic_button: 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 Asterdex. Nothing to install.
panic_button 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 panic_button 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 panic_button. 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.
panic_button is provided by the Asterdex MCP server (tyranosurasmax/asterdex-mcp-server). 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 →