Pi-hole MCP Server

Pi-hole MCP Server

A server that exposes Pi-hole functionality as tools for AI assistants, allowing them to retrieve local DNS settings and query history through natural language.

Category
访问服务器

README

pihole-mcp-serer

A Model Context Protocol (MCP) server for Pi-hole. This server exposes Pi-hole functionality as tools that can be used by AI assistants.

Features

  • ListLocalDNS: Returns all local DNS settings from Pi-hole
  • ListQueries: Returns recent DNS query history from Pi-hole
  • Multiple Pi-hole Support: Manage up to 4 Pi-holes from a single MCP server
  • ...more to come...

Dependencies

Docker

uv (Optional, for Development)

If you want to run the application locally, use uv. Install it with your package manager of choice.

Environment

Create a .env file in the project root with your Pi-hole credentials:

# Primary Pi-hole (required)
PIHOLE_URL=https://your-pihole.local/
PIHOLE_PASSWORD=your-admin-password
#PIHOLE_NAME=Primary        # optional, defaults to URL if unset

# Secondary Pi-hole (optional)
#PIHOLE2_URL=https://secondary-pihole.local/
#PIHOLE2_PASSWORD=password2
#PIHOLE2_NAME=Secondary     # optional

# Up to 4 Pi-holes:
#PIHOLE3_URL=...
#PIHOLE3_PASSWORD=...
#PIHOLE3_NAME=...

#PIHOLE4_URL=...
#PIHOLE4_PASSWORD=...
#PIHOLE4_NAME=...

Docker Deployment

Run the Pi-hole MCP server in Docker.

Using Docker Compose

  1. Pull and start the container:

    docker-compose up -d
    
  2. The server will be available at http://localhost:8383

Manual Docker Build

Alternatively, you can build and run the Docker container manually:

docker build -t pihole-mcp .
docker run -p 8383:8000 --env-file .env -d pihole-mcp

Run Locally

The Docker deployment uses SSE mode for two-way communication between the host and container. You could (theoretically) use STDIO mode with Docker exec. If you want to run it locally, though, you can simply run it with uv. This is particularly useful for quickly inspecting tools and resources with the inbuilt mcp dev utilities. For example:

uv run mcp dev main.py

Then in your web browser navigate to http://localhost:6274.

API

This MCP server exposes the following resources and tools:

Resources

  • piholes://: Returns information about all configured Pi-holes

Tools

  • list_local_dns: Lists all local DNS settings from Pi-hole(s)
  • list_queries: Fetches the recent DNS query history from Pi-hole(s)

Each tool call returns results as a list of dictionaries with the following structure:

[
  {
    "pihole": "Pi-hole Name",
    "data": [...]  # Result data from this Pi-hole
  },
  ...
]

Testing in goose

Goose is a CLI LLM client that's useful for testing and development. Follow their install instructions here.

The following assumes you've completed the initial setup with goose configure.

Configure Extension

  1. Type goose configure to open the configuration menu.
  2. Select Add Extension
  3. Select Remote Extension
  4. It will ask for a name. It doesn't matter what you name it. I called mine pihole-mcp.
  5. When it asks "What is the SSE endpoint URI?" enter http://localhost:8383/sse.
  6. Enter a timeout.
  7. Add a description if you'd like.
  8. Select No when it asks about environment variables. Screenshot of configuration

Start a Session

Once the server is installed, start a chat session.

goose session

Try asking it: "What are my local DNS records?"

Screenshot of local DNS tool

...or telling it: "Show me my recent DNS queries."

Screenshot of queries

Claude Desktop

Claude's desktop client currently only support's the STDIO protocol, however you can use a proxy to communicate with the SSE endpoint.

Add the following to your claude_desktop_config.json file.

{
  "mcpServers": {
    "pihole": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8383/sse"
      ]
    }
  }
}

If you're connecting to a different host on your local network and using an unsecured connection, you'll need to explicitly allow it with the --allow-http argument. For example:

{
  "mcpServers": {
    "pihole": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://192.168.1.255:8383/sse",
        "--allow-http"
      ]
    }
  }
}

Afterwards, completely restart the application and try it out.

Claude DNS info

Claude query info

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选