AI agents call pbs_status 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 only retrieves and displays existing backup datastore metrics (space utilization). It performs no modifications, deletions, or external operations. While it provides operational visibility into the backup infrastructure, reading status information poses minimal risk—an AI agent misusing this tool could at worst gain information about storage capacity, which does not constitute a security or safety…
From the tool's definition The tool description explicitly states it 'Show[s] Proxmox Backup Server datastore usage: total, used, and available space per datastore.' This is a query/reporting operation that retrieves status information without modifying any state.
Attacks that exploit this kind of access
Show Proxmox Backup Server datastore usage: total, used, and available space per datastore. 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 pbs_status: 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.
pbs_status 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 pbs_status 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 pbs_status. 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.
pbs_status 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 →