Cancel an RFQ.
AI agents call cancel_rfq to permanently remove resources in Bybit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling an RFQ removes an active trading request from the exchange. Like other cancel operations (cancel_all_orders, batch_cancel_order on the same server), this is a destructive action that permanently terminates the RFQ and cannot be reversed. In a financial trading context, this carries high severity as it can disrupt negotiated trades or hedging strategies.
From the tool's definition Cancel an RFQ — cancelling a Request for Quote is an irreversible termination of a live trading request that cannot be undone once submitted.
Attacks that exploit this kind of access
Cancel an RFQ. It is categorised as a Destructive tool in the Bybit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Bybit MCP server in PolicyLayer and add a rule for cancel_rfq: 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 Bybit. Nothing to install.
cancel_rfq 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_rfq 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_rfq. 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_rfq is provided by the Bybit MCP server (johnnywic/bybit-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 →