Get real-time performance metrics for a server (CPU, disk I/O, network). Queries the Hetzner Metrics API and returns summarised stats: - cpu: current usage %, period average, peak (auto-calculated from core count) - disk: read/write bandwidth (MB/s) and IOPS for the first disk - network: inbound/...
AI agents call hetzner_get_server_metrics to retrieve information from Hetzner MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely reads and queries monitoring data from the Hetzner Metrics API without side effects. It returns performance statistics (CPU %, disk I/O, network bandwidth) for a specified server. No resources are created, modified, deleted, or executed.
From the tool's definition Tool retrieves "real-time performance metrics" and "Queries the Hetzner Metrics API and returns summarised stats" for CPU, disk, and network data. No modification, deletion, or execution of commands occurs.
Attacks that exploit this kind of access
Get real-time performance metrics for a server (CPU, disk I/O, network). Queries the Hetzner Metrics API and returns summarised stats: - cpu: current usage %, period average, peak (auto-calculated from core count) - disk: read/write bandwidth (MB/s) and IOPS for the first disk - network: inbound/outbound bandwidth (Mbps) for the first interface Default window: last 5 minutes, 60-second step. Metrics are retained for 30 days; step is auto-adjusted to a max of 500 samples. It is categorised as a Read tool in the Hetzner MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hetzner MCP Server MCP server in PolicyLayer and add a rule for hetzner_get_server_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 Hetzner MCP Server. Nothing to install.
hetzner_get_server_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 hetzner_get_server_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 hetzner_get_server_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.
hetzner_get_server_metrics is provided by the Hetzner MCP Server MCP server (jurislm/hetzner-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 →