AI agents call adguard_stats 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 displays DNS query statistics from AdGuard Home without creating, modifying, deleting, or executing any operations. It is a read-only query of existing monitoring data, presenting no risk of unintended changes to the system. The low severity reflects minimal blast radius even if misused by an agent.
From the tool's definition Tool description explicitly states 'Show AdGuard Home DNS query stats: total queries, blocked count, block rate, top queried and blocked domains.' The verb 'show' and the nature of the requested data (statistics, counts, rates, domain lists) indicate pure…
Attacks that exploit this kind of access
Show AdGuard Home DNS query stats: total queries, blocked count, block rate, top queried and blocked domains. 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 adguard_stats: 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.
adguard_stats 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 adguard_stats 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 adguard_stats. 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.
adguard_stats 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 →