AI agents call adguard_check_host 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 a lookup/query of existing AdGuard Home blocking rules and returns whether a domain matches them. It has no side effects, creates no changes to configuration or data, and does not execute commands or delete anything. It is purely informational, fitting the Read category definition of 'retrieves or queries data; no side effects'.
From the tool's definition Tool description states 'Check if a domain is blocked' - a query operation that retrieves blocking status and matching rule information without modifying any state or triggering external actions.
Attacks that exploit this kind of access
Check if a domain is blocked by AdGuard Home and which rule matches. 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_check_host: 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_check_host 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_check_host 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_check_host. 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_check_host 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 →