Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-homelab-server List all running Docker containers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol server for homelab management Give AI agents access to your homelab: Docker, Ollama, system stats, and more.
An MCP (Model Context Protocol) server that exposes homelab tools to AI agents like Claude, GPT, or any MCP-compatible client. Instead of writing scripts yourself, just ask your AI agent to manage your infrastructure.
Example conversations:
"List all running Docker containers"
"How much RAM is Ollama using?"
"Pull the llama3 model"
"Show me disk usage on the server"
Related MCP server: System Monitor MCP Server
Tool | Description |
| List running containers |
| Get container logs |
| Restart a container |
| Stop a container |
| Resource usage (CPU, RAM, network) |
Tool | Description |
| List installed models |
| Pull a new model |
| Show running models and memory usage |
| Run a quick inference test |
Tool | Description |
| CPU, RAM, disk, uptime |
| Detailed disk usage by mount |
| Network interfaces and connections |
| Top processes by CPU/RAM |
Add to your MCP client configuration:
{
"mcpServers": {
"homelab": {
"command": "npx",
"args": ["-y", "@anthropic/mcp-server-homelab"]
}
}
}{
"mcpServers": {
"homelab": {
"command": "python3",
"args": ["path/to/mcp-homelab-server/src/server.py"]
}
}
}git clone https://github.com/Proto-labs-rnd/mcp-homelab-server.git
cd mcp-homelab-server
pip install -r requirements.txt
python3 src/server.pyPython 3.10+
Docker (for Docker tools)
Ollama (for LLM tools, optional)
Linux/macOS (system stats rely on standard Unix tools)
MCP Client (Claude, Cursor, OpenClaw, etc.)
│
▼
┌─────────────────────┐
│ MCP Server (stdio) │
│ ┌───────────────┐ │
│ │ Docker Tools │ │
│ │ Ollama Tools │ │
│ │ System Tools │ │
│ └───────────────┘ │
└─────────────────────┘
│
▼
Your HomelabMIT
This server cannot be deployed
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Give your AI agents the tools to build, manage, and run automation workflows.
