AI agents call get_rfq_realtime 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 real-time RFQ (Request For Quote) data from the Bybit exchange. It is a read-only query that has no side effects on account state, positions, or financial obligations. The low severity reflects that misuse would only expose market data the user already has access to, with no capability to execute trades or modify account state.
From the tool's definition Tool name 'get_rfq_realtime' and description 'Get RFQs in real-time' indicate a retrieval operation. RFQ stands for Request For Quote, which is market data. No modification, deletion, execution, or financial commitment occurs.
Attacks that exploit this kind of access
Get RFQs in real-time. 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_rfq_realtime: 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_rfq_realtime 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_rfq_realtime 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_rfq_realtime. 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_rfq_realtime is provided by the Bybit MCP server (johnnywic/bybit-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 →