Libvirt Mcp

What is Libvirt Mcp about?

Provides an experimental MCP server that connects Libvirt with large language models (e.g., Granite) through Ollama, enabling AI‑driven commands for virtual machine lifecycle management.

How to use Libvirt Mcp?

1. Clone and install mcp-cli:

   git clone https://github.com/chrishayuk/mcp-cli
   pip3.11 install -e "[.][cli,dev]"
   

2. Install ollama and pull the desired model:

   curl -fsSL https://ollama.com/install.sh | sh
   ollama serve >/dev/null 2>&1 &
   ollama pull granite3.2:8b-instruct-q8_0
   

3. Install uv (Python dependency manager):

   pip install uv
   

4. Install required system libraries:

   dnf install -y libvirt-devel python3-devel
   

5. Inside the libvirt-mcp directory, synchronize Python dependencies:

   uv sync
   

6. Edit server_config.json to point to the correct libvirt‑mcp server path.
7. Run the server with the provided script:

   ./run.sh
   

   This script launches the MCP server using Ollama as the provider and Granite as the model.

Key features of Libvirt Mcp

• AI‑backed control of Libvirt virtual machines via natural language.
• Seamless integration with Ollama for local LLM hosting.
• Simple setup using uv for Python dependency management.
• Configurable server path through server_config.json.
• Debugging support with the mcp CLI tool.

Use cases of Libvirt Mcp

• Automating VM provisioning, start/stop, and snapshot operations through conversational prompts.
• Rapid prototyping of virtualization workflows without writing CLI commands.
• Educational demos showing how AI can manage infrastructure.
• Remote administration where only natural‑language instructions are feasible.

FAQ from the Libvirt Mcp

Q: Which model does the server use by default? A: The example uses granite3.2:8b-instruct-q8_0 pulled from Ollama.

Q: Can I use a different LLM provider? A: Yes, as long as the provider is supported by Ollama and the model is available locally.

Q: Do I need root privileges to manage VMs? A: Libvirt operations typically require appropriate permissions; run the server with a user that has access to the libvirt socket.

Q: How do I debug issues? A: Install the mcp CLI (pip install mcp) and run mcp dev setup.py to inspect the server behavior.

Q: Is there a Windows support? A: The instructions target Fedora/RHEL (dnf). On Windows, use equivalent package managers and ensure Libvirt and Python bindings are installed.

libvirt-mcp

This is an experimental mcp server for libvirt. The following lines explain how to use it with mcp-cli and ollama. First, install mcp-cli:

git clone https://github.com/chrishayuk/mcp-cli
pip3.11 install -e ".[cli,dev]"

Then, install ollama:

curl -fsSL https://ollama.com/install.sh | sh
ollama serve >/dev/null 2>&1  &
ollama pull granite3.2:8b-instruct-q8_0

You need also uv:

pip install uv

You need the following python bindings:

dnf install -y libvirt-devel python3-devel

Then, in the libvirt-mcp directory, first install the dependencies by running:

uv sync

Then, edit server_config.json and set up the correct path to the libvirt-mcp server. Finally, execute run.sh, that uses ollama as provider and granite as model.

For debugging, you can install mcp:

dnf install -y npm
pip install mcp

And then, run:

mcp dev setup.py