AI agents use set_auto_add_margin 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/position configuration settings (enabling or disabling auto-margin replenishment) rather than executing trades or moving funds directly. It is reversible—the setting can be toggled back. However, it carries high severity because incorrect auto-margin settings could lead to unintended liquidations or cascading margin calls if an agent misconfigures it during volatile market conditions.
From the tool's definition Tool name 'set_auto_add_margin' and description 'Set auto add margin for a position' indicate modification of account settings that affect position management and margin behavior.
Attacks that exploit this kind of access
Set auto add margin for a position. 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_auto_add_margin: 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_auto_add_margin 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_auto_add_margin 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_auto_add_margin. 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_auto_add_margin 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 →