AI agents call get_gpu to retrieve information from HomeLab Monitor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves GPU information from the homelab monitor. As a read-only query operation with no side effects, it falls under the Read category. The severity is low because it only exposes monitoring/telemetry data about GPU status without permitting modifications or dangerous operations. High confidence based on naming convention and read-only server design, despite empty description.
From the tool's definition Tool name 'get_gpu' follows the 'get_' naming pattern consistent with sibling tools like 'get_ai_models', 'get_alerts', 'get_containers', etc. Server is described as 'read-only MCP server'.
Documented attack patterns abuse exactly the kind of access get_gpu gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HomeLab Monitor, and nothing reaches the server without passing your rules. This is the rule we recommend for get_gpu:
{
"version": "1",
"default": "deny",
"tools": {
"get_gpu": {}
}
}get_gpu is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_gpu. It is categorised as a Read tool in the HomeLab Monitor MCP Server, which means it retrieves data without modifying state.
Register the HomeLab Monitor MCP server in PolicyLayer and add a rule for get_gpu: 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 Monitor. Nothing to install.
get_gpu 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 get_gpu 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 get_gpu. 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.
get_gpu is provided by the HomeLab Monitor MCP server (sikamikanikobg/homelab-monitor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 HomeLab Monitor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 HomeLab Monitor tools catalogued and risk-classified — across an index of 42,500+ MCP servers.