Get training logs from a VPS run
AI agents call vps_logs 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.
The tool fetches/reads training logs from a remote VPS. This is a pure read operation with no modification, execution, or destructive capability implied. Low severity as logs may contain sensitive information like credentials or data paths, but the blast radius of misuse is minimal.
From the tool's definition 'Get training logs from a VPS run' — retrieves log data with no side effects
Attacks that exploit this kind of access
Get training logs from a VPS run. 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_logs: 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_logs 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_logs 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_logs. 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_logs 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 →