Switch between ONE_WAY and HEDGE position mode.
AI agents invoke change_position_mode to trigger actions in Bitunix MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Changing position mode alters how the exchange handles open positions and orders (one-way vs hedge). This is an operational configuration change that triggers external state changes on the exchange, affecting how trades are executed and managed. It doesn't directly move money but can significantly impact open positions and risk exposure.
From the tool's definition Switch between ONE_WAY and HEDGE position mode
Attacks that exploit this kind of access
Switch between ONE_WAY and HEDGE position mode. It is categorised as a Execute tool in the Bitunix MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bitunix MCP server in PolicyLayer and add a rule for change_position_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_position_mode is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the change_position_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_position_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_position_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 →