AI agents call media_dashboard 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 performs read-only queries across multiple homelab systems and aggregates status information for display. It has no side effects, creates no changes, executes no code, and poses minimal risk if called by an AI agent. The low severity reflects that exposing dashboards and monitoring data carries negligible blast radius in a homelab context.
From the tool's definition Tool retrieves and displays status information: 'Proxmox node health, container status, active downloads, library stats, and storage — all in a single call.' No modification, deletion, or execution of commands is described.
Attacks that exploit this kind of access
All-in-one homelab status: Proxmox node health, container status, active downloads, library stats, and storage — all in a single call. 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 media_dashboard: 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.
media_dashboard 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 media_dashboard 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 media_dashboard. 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.
media_dashboard 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 →