Gives AI assistants full control over your Pi-hole instance — DNS blocking, domain management, query analysis, statistics, network devices, DHCP, and
Pihole MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Gives AI assistants full control over your Pi-hole instance — DNS blocking, domain management, query analysis, statistics, network devices, DHCP, and system administration. Compatible with the Pi-hole v6 REST API.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Once Pihole MCP is connected, these are the calls the assistant has available:
Homebrew — Installs on both macOS and Linux (Homebrew on Linux). On macOS the cask clears the quarantine attribute during install, so the binary runs without aDashboard — The Dashboard tool exposed by this serverStatistics — The Statistics tool exposed by this serverSystem — The System tool exposed by this serverTransport — By default, pihole-mcp uses stdio (standard for MCP). HTTP and SSE transports are also available:OpenTelemetry — All tool calls are automatically traced with tool name, duration, and error statusYou will need 8 environment variables: PIHOLE_URL, PIHOLE_PASSWORD, PIHOLE_1_URL, PIHOLE_1_PASSWORD, PIHOLE_1_NAME, PIHOLE_2_URL, PIHOLE_2_PASSWORD, PIHOLE_2_NAME. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Pihole MCP's toolset — Homebrew, Dashboard, Statistics and 3 more — is a fair guide to whether it matches your workflow. It is maintained by lloydmcl; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Pihole MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Homebrew | Installs on both macOS and Linux (Homebrew on Linux). On macOS the cask clears the quarantine attribute during install, so the binary runs without a Gatekeeper prompt. |
| Dashboard | The Dashboard tool exposed by this server. |
| Statistics | The Statistics tool exposed by this server. |
| System | The System tool exposed by this server. |
| Transport | By default, pihole-mcp uses stdio (standard for MCP). HTTP and SSE transports are also available: |
| OpenTelemetry | All tool calls are automatically traced with tool name, duration, and error status. |
{
"mcpServers": {
"pihole": {
"command": "pihole-mcp",
"env": {
"PIHOLE_URL": "http://192.168.1.2",
"PIHOLE_PASSWORD": "your-password"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PIHOLE_URL | Endpoint or connection string the server talks to. | Yes |
| PIHOLE_PASSWORD | Configuration value read at startup. | Optional |
| PIHOLE_1_URL | Endpoint or connection string the server talks to. | Yes |
| PIHOLE_1_PASSWORD | Configuration value read at startup. | Optional |
| PIHOLE_1_NAME | Configuration value read at startup. | Optional |
| PIHOLE_2_URL | Endpoint or connection string the server talks to. | Yes |
| PIHOLE_2_PASSWORD | Configuration value read at startup. | Optional |
| PIHOLE_2_NAME | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.