Register a remote VPS for training (any SSH-accessible machine)
AI agents use vps_register to create or update resources in ML Lab MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ML Lab MCP environment.
Registering a VPS creates a new record/configuration entry linking a remote machine to the ML Lab environment. This is a reversible write operation (the registration can be removed), not destructive. However, it does establish SSH access to a remote machine, which has moderate blast radius if misused — an attacker could register a malicious VPS or register unintended machines.
From the tool's definition Register a remote VPS for training (any SSH-accessible machine)
Attacks that exploit this kind of access
Register a remote VPS for training (any SSH-accessible machine). It is categorised as a Write tool in the ML Lab MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ML Lab MCP server in PolicyLayer and add a rule for vps_register: 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_register 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 vps_register 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_register. 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_register 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 →