Set leverage for a specific symbol
AI agents use set_leverage to create or update resources in Bybit MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bybit MCP Server environment.
Setting leverage modifies account/position configuration on a live exchange. While it doesn't directly move money or place trades, it alters risk exposure significantly — incorrect leverage can amplify losses dramatically. It is reversible (leverage can be changed back), so Write is appropriate over Destructive, but severity is high due to the financial risk amplification effect if misused by an AI agent.
From the tool's definition 'Set leverage for a specific symbol' — modifies the leverage setting on a trading position/symbol on Bybit exchange
Attacks that exploit this kind of access
Set leverage for a specific symbol. It is categorised as a Write tool in the Bybit MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bybit MCP Server MCP server in PolicyLayer and add a rule for set_leverage: 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 MCP Server. Nothing to install.
set_leverage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_leverage 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 set_leverage. 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.
set_leverage is provided by the Bybit MCP Server MCP server (kondisettyravi/mcp-bybit-node). 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 →