AI agents call get_risk_status to retrieve information from Bybit Ws without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves current risk metrics and status information from Bybit. It performs no write operations, does not execute trades or commands, does not delete data, and does not move money. It is a read-only diagnostic tool for monitoring account risk parameters.
From the tool's definition Tool name is 'get_risk_status' and description states 'Get risk limits and current usage' — purely retrieval operations (daily PnL vs max_daily_loss, margin vs max_total_margin, entry blocked status). No modification, deletion, or execution of trades/commands.
Attacks that exploit this kind of access
Get risk limits and current usage: daily PnL vs max_daily_loss, margin vs max_total_margin, entry blocked status. It is categorised as a Read tool in the Bybit Ws MCP Server, which means it retrieves data without modifying state.
Register the Bybit Ws MCP server in PolicyLayer and add a rule for get_risk_status: 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 Ws. Nothing to install.
get_risk_status 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_risk_status 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_risk_status. 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_risk_status is provided by the Bybit Ws MCP server (poliakarmai/bybit-ws). 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 →