AI agents call get_closed_pnl to retrieve information from Bybit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical P&L (profit/loss) data from closed positions on a cryptocurrency exchange. It has no side effects and performs a pure data query operation, placing it in the Read category. Severity is medium rather than low because access to detailed financial trading history could be sensitive information that an AI agent might leak or misuse, though the tool itself is non-destructive.
From the tool's definition Tool name 'get_closed_pnl' indicates retrieval of closed profit/loss data. The sibling tools on this server include read-only market and account query functions (get_account_info, get_coin_balance, get_kline, get_order_history), establishing a pattern of Read…
Attacks that exploit this kind of access
get_closed_pnl. It is categorised as a Read tool in the Bybit MCP Server, which means it retrieves data without modifying state.
Register the Bybit MCP server in PolicyLayer and add a rule for get_closed_pnl: 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. Nothing to install.
get_closed_pnl 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 get_closed_pnl 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 get_closed_pnl. 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.
get_closed_pnl is provided by the Bybit MCP server (workspace/bybit-mcp-server). 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 →