Remove a domain from the allow or deny list.
AI agents call remove_domain to permanently remove resources in Mcp Pihole — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a domain from allow/deny lists is an irreversible deletion of a configuration entry. If misused, an AI agent could remove critical block rules (allowing malicious domains) or remove allow-list entries (breaking legitimate access), with significant security and availability impact. This matches the Destructive category as the deletion cannot be undone without re-adding the entry manually.
From the tool's definition 'Remove a domain from the allow or deny list' — permanently removes a domain entry from Pi-hole's filtering configuration
Attacks that exploit this kind of access
Remove a domain from the allow or deny list. It is categorised as a Destructive tool in the Mcp Pihole MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Pihole MCP server in PolicyLayer and add a rule for remove_domain: 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 Mcp Pihole. Nothing to install.
remove_domain is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_domain 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 remove_domain. 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.
remove_domain is provided by the Mcp Pihole MCP server (obrien-matthew/mcp-pihole). 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 →