AI agents use manual_borrow to commit financial operations through Bybit — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Borrowing funds commits a financial obligation (debt/interest liability) on the account. Misuse could result in unauthorized leverage, interest charges, or margin risk — clearly a financial action with high blast radius.
From the tool's definition Manually borrow funds in unified margin account
Attacks that exploit this kind of access
Manually borrow funds in unified margin account. It is categorised as a Financial tool in the Bybit MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Bybit MCP server in PolicyLayer and add a rule for manual_borrow: 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.
manual_borrow is a Financial 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 manual_borrow 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 manual_borrow. 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.
manual_borrow 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 →