AI agents use set_collateral_coin 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 account-level settings (collateral coin configuration) which affects trading position management and collateral handling. While reversible (can be toggled on/off), it's a Write operation rather than Read. Severity is high because misuse could alter account risk parameters or collateral structure, potentially exposing positions to liquidation risk or locking funds in unintended collateral assets.
From the tool's definition Tool name 'set_collateral_coin' and description 'Set collateral coin on or off' indicate modification of account collateral settings. This is a reversible write operation that changes trading account configuration.
Attacks that exploit this kind of access
Set collateral coin on or off. 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_collateral_coin: 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_collateral_coin 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_collateral_coin 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_collateral_coin. 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_collateral_coin 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 →