AI agents call btse_position_risk to retrieve information from Btse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and calculates derived metrics from an existing open position. It performs no state-modifying operations on the account, positions, or orders. The computation is informational and supports decision-making but does not execute trades, move funds, or alter any data.
From the tool's definition Tool description: 'Compute liquidation price, unrealised PnL, and risk flag for an open position.' The verb 'compute' and the outputs (liquidation price, unrealised PnL, risk flag) are all read-only analytics derived from existing position data.
Attacks that exploit this kind of access
Compute liquidation price, unrealised PnL, and risk flag for an open position. It is categorised as a Read tool in the Btse MCP Server, which means it retrieves data without modifying state.
Register the Btse MCP server in PolicyLayer and add a rule for btse_position_risk: 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 Btse. Nothing to install.
btse_position_risk is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the btse_position_risk 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 btse_position_risk. 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.
btse_position_risk is provided by the Btse MCP server (xbotlive/btse-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 →