change_margin_mode
AI agents use change_margin_mode to commit financial operations through Bitunix MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool operates on a financial trading platform that explicitly supports futures trading with leverage. Changing margin mode (e.g., between cross and isolated margin) directly affects how losses are calculated and how much capital is at risk across positions.
From the tool's definition Tool name 'change_margin_mode' on a trading/futures exchange MCP server (Bitunix) that supports 'futures and spot trading with advanced order management, leverage, and TP/SL'
Attacks that exploit this kind of access
change_margin_mode. It is categorised as a Financial tool in the Bitunix MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Bitunix MCP server in PolicyLayer and add a rule for change_margin_mode: 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 Bitunix MCP. Nothing to install.
change_margin_mode 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 change_margin_mode 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 change_margin_mode. 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.
change_margin_mode is provided by the Bitunix MCP server (luiinventions/bitunix-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 →