What are the dependencies?
Docker is required for production deployment. For development, `uv` is optional to run the server locally.
@sbarbett
Basic information
A Model Context Protocol (MCP) server for Pi-hole
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"pihole-mcp-server": {
"command": "uv",
"args": [
"run",
"mcp",
"dev",
"main.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The π pihole-mcp-serer is a Model Context Protocol (MCP) server that exposes Pi-hole functionality as tools for AI assistants. It allows AI tools to manage local DNS records, query DNS history, and retrieve metrics from one or multiple Pi-hole instances.
Create a .env file with PIHOLE_URL and PIHOLE_PASSWORD (and optionally up to three additional Pi-holes). Run the server via Docker (docker-compose up -d) for production or with uv run mcp dev main.py for development. Then configure an MCP client (e.g., Goose or Claude Desktop) to connect to the SSE endpoint at http://localhost:8383/sse.
Docker is required for production deployment. For development, `uv` is optional to run the server locally.
Add `PIHOLE2_URL`, `PIHOLE2_PASSWORD`, and optionally `PIHOLE2_NAME` in the `.env` file. Repeat for up to four Pi-holes.
Use `uv run mcp dev main.py` after installing `uv` and any required dependencies.
The server uses SSE (Server-Sent Events) on port 8383 by default. Clients like Goose connect directly; Claude Desktop uses a proxy (`mcp-remote`) to bridge STDIO to SSE.
Credentials are set via environment variables (`PIHOLE_URL`, `PIHOLE_PASSWORD`) in the `.env` file. No other authentication mechanism is documented.
π The fast, Pythonic way to build MCP servers and clients.
A search tool helps dev to solve the naming things problem.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Open-source MCP to use Blender with any LLM

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
Comments