AI agents use set_mmp 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.
Setting MMP parameters is a configuration change that adjusts trading protection thresholds and behaviors. This is reversible (parameters can be adjusted again) and does not irreversibly delete data or execute arbitrary code. While it affects trading operations, it is not immediately financial (no money moves) and not destructive.
From the tool's definition Tool name 'set_mmp' and description 'Set Market Maker Protection (MMP) parameters' indicate configuration modification of trading protection settings. The verb 'set' in both name and description confirms this creates or modifies data reversibly.
Attacks that exploit this kind of access
Set Market Maker Protection (MMP) parameters. 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_mmp: 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_mmp 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_mmp 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_mmp. 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_mmp 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 →