AI agents use set_trading_stop to commit financial operations through Bybit — usually the final step of a payment, billing, or trading workflow. A call moves real money.
On a cryptocurrency exchange like Bybit, 'set_trading_stop' almost certainly sets stop-loss or take-profit levels on trading positions. This directly affects financial outcomes — it can trigger automatic position closures at specified price levels, committing or protecting financial assets.
From the tool's definition Tool name 'set_trading_stop' on a Bybit trading exchange MCP server with 246 tools for 'trading, account management, and more'. Server context includes order management tools like amend_order, cancel_all_orders, batch_place_order.
Attacks that exploit this kind of access
set_trading_stop. It is categorised as a Financial tool in the Bybit MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Bybit MCP server in PolicyLayer and add a rule for set_trading_stop: 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.
set_trading_stop 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 set_trading_stop 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 set_trading_stop. 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.
set_trading_stop 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 →