Close an open position on Hyperliquid and realize profit/loss. Submits a reduce-only market order. Returns entry price, exit price, P&L in USD and percentage, and fees paid.
AI agents use trading_close_position to commit financial operations through Purple Flea Trading — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool executes a live trade on a perpetual futures exchange, realizing profit or loss and paying fees. It directly commits financial obligations and moves funds, qualifying as Financial. Misuse by an AI agent could result in forced liquidation of positions, unintended realized losses, and irreversible financial impact — hence critical severity.
From the tool's definition Close an open position on Hyperliquid and realize profit/loss. Submits a reduce-only market order. Returns entry price, exit price, P&L in USD and percentage, and fees paid.
Attacks that exploit this kind of access
Close an open position on Hyperliquid and realize profit/loss. Submits a reduce-only market order. Returns entry price, exit price, P&L in USD and percentage, and fees paid. It is categorised as a Financial tool in the Purple Flea Trading MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Purple Flea Trading MCP server in PolicyLayer and add a rule for trading_close_position: 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 Purple Flea Trading. Nothing to install.
trading_close_position 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 trading_close_position 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 trading_close_position. 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.
trading_close_position is provided by the Purple Flea Trading MCP server (purple-flea/agent-trading). 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 →