Disable Pi-hole ad blocking. Optionally specify duration in seconds.
AI agents use disable_pihole to create or update resources in Pi-hole MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pi-hole MCP Server environment.
This tool modifies the operational state of Pi-hole by disabling DNS-level ad blocking, which affects all devices on the network. It is reversible (blocking can be re-enabled), so it falls under Write rather than Destructive. However, the blast radius is high because disabling network-wide DNS filtering exposes all connected devices to ads and potentially malicious domains until re-enabled.
From the tool's definition Disable Pi-hole ad blocking. Optionally specify duration in seconds.
Attacks that exploit this kind of access
Disable Pi-hole ad blocking. Optionally specify duration in seconds. It is categorised as a Write tool in the Pi-hole MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pi-hole MCP Server MCP server in PolicyLayer and add a rule for disable_pihole: 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 Pi-hole MCP Server. Nothing to install.
disable_pihole is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the disable_pihole 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 disable_pihole. 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.
disable_pihole is provided by the Pi-hole MCP Server MCP server (sebszczec/pihole-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 →