AI agents call proxmox_get_node_metrics to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries resource metrics from the Proxmox node—standard monitoring information. It performs no state changes, data modifications, code execution, or destructive operations. The blast radius of misuse is minimal; an agent could only gather system information that would typically be available to any authorized user. This is a straightforward Read operation.
From the tool's definition Tool name 'proxmox_get_node_metrics' and description 'Get resource usage (CPU, RAM, disk, load average, uptime)' indicate a read-only retrieval of monitoring data with no modification or side effects.
Attacks that exploit this kind of access
Get resource usage (CPU, RAM, disk, load average, uptime) for the Proxmox node itself. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for proxmox_get_node_metrics: 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 Homelab. Nothing to install.
proxmox_get_node_metrics 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 proxmox_get_node_metrics 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 proxmox_get_node_metrics. 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.
proxmox_get_node_metrics is provided by the Homelab MCP server (nainounen/homelab-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 →