Track MiniMax usage across sessions for self-improvement.
AI agents call minimax_session_tracker to retrieve information from My Minimax without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to read and aggregate usage data across sessions for reporting and self-improvement purposes. This is primarily a read/analytics operation with no indication of destructive, financial, or execution side effects. Confidence is moderate because the description is vague and 'self-improvement' could imply some write behavior (storing session data), but the primary framing is tracking/monitoring.
From the tool's definition 'Track MiniMax usage across sessions' — monitoring/tracking usage metrics
Attacks that exploit this kind of access
Track MiniMax usage across sessions for self-improvement. It is categorised as a Read tool in the My Minimax MCP Server, which means it retrieves data without modifying state.
Register the My Minimax MCP server in PolicyLayer and add a rule for minimax_session_tracker: 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 My Minimax. Nothing to install.
minimax_session_tracker is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the minimax_session_tracker 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 minimax_session_tracker. 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.
minimax_session_tracker is provided by the My Minimax MCP server (wongo/my-minimax-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 →