AI agents use manual_repay_no_convert to commit financial operations through Bybit — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Repaying a loan or margin debt is a financial operation that moves funds and settles financial obligations. On a crypto exchange like Bybit, this would involve transferring assets to repay borrowed funds, which is a Financial category action. The 'without asset conversion' qualifier specifies a mode of repayment but doesn't change the financial nature of the action.
From the tool's definition Manual repay without asset conversion — 'repay' indicates a financial obligation action involving debt repayment on the Bybit exchange
Attacks that exploit this kind of access
Manual repay without asset conversion. 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_repay_no_convert: 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_repay_no_convert 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_repay_no_convert 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_repay_no_convert. 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_repay_no_convert 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 →