AI agents use set_price_limit_behaviour to create or update resources in Bybit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bybit environment.
This tool modifies configuration settings for an exchange account, which qualifies as a Write action (reversible configuration change). Severity is high because misconfiguring price limit behavior could cause unintended order executions, rejections, or losses if an AI agent sets it inappropriately.
From the tool's definition The tool description 'Set price limit behaviour (allow system to modify order price or reject)' indicates it modifies trading parameters that affect order execution behavior.
Attacks that exploit this kind of access
Set price limit behaviour (allow system to modify order price or reject). It is categorised as a Write tool in the Bybit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bybit MCP server in PolicyLayer and add a rule for set_price_limit_behaviour: 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_price_limit_behaviour is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_price_limit_behaviour 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_price_limit_behaviour. 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_price_limit_behaviour 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 →