AI agents call find_arbitrage_pairs 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.
The tool name indicates data retrieval (find/search) of arbitrage pairs, which aligns with Read category. On a trading exchange MCP, this likely queries market data or pair information. However, confidence is moderate (0.60) due to the empty description—it's possible the tool could trigger automated trading or execute strategies, which would elevate it to Execute.
From the tool's definition Tool name 'find_arbitrage_pairs' suggests querying or searching for arbitrage opportunities across market pairs, with no explicit modification or execution language. However, description is empty.
Attacks that exploit this kind of access
find_arbitrage_pairs. 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 find_arbitrage_pairs: 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.
find_arbitrage_pairs 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 find_arbitrage_pairs 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 find_arbitrage_pairs. 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.
find_arbitrage_pairs 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 →