Check status of a VPS (online, GPU usage, running jobs)
AI agents call vps_status to retrieve information from ML Lab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves operational information about a VPS instance (online/offline status, GPU metrics, job listing). It performs no modifications, executions, or destructive actions. While it provides infrastructure visibility that could inform malicious actor planning, the tool itself is informational only.
From the tool's definition vps_status checks status of a VPS: online state, GPU usage, running jobs. These are read-only queries with no side effects or modifications.
Attacks that exploit this kind of access
Check status of a VPS (online, GPU usage, running jobs). It is categorised as a Read tool in the ML Lab MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Lab MCP server in PolicyLayer and add a rule for vps_status: 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 ML Lab MCP. Nothing to install.
vps_status 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 vps_status 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 vps_status. 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.
vps_status is provided by the ML Lab MCP server (pushpullcommitpush/ml-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 →