About Proxmox MCP Server
Proxmox MCP Server connects LLMs to Proxmox VE infrastructure information, including cluster, node, and virtual machine details. It supports Docker deployment and reads credentials from environment variables.
Key features
- 01Get cluster information
- 02Query node details
- 03Get VM details and status
- 04List cluster VMs
- 05Docker and Docker Compose deployment
- 06Environment-variable credential management
Use cases
- 01Inspect Proxmox cluster information
- 02Check a node's details
- 03Review VM status and details
- 04List virtual machines in a cluster
MCP support
Exposes MCP endpoints for retrieving Proxmox cluster, node, and VM information, including listing all VMs, to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEProxmox MCP Server
This is a Model Context Protocol (MCP) server that interfaces with a Proxmox VE server to provide infrastructure context to LLMs. The server exposes various endpoints that allow LLMs to query information about the Proxmox cluster, nodes, and virtual machines.
Features
- Get cluster-wide information
- Query specific node details
- Get VM information and status
- List all VMs in the cluster
- Docker and Docker Compose support for easy deployment
- Secure credential management through environment variables
Prerequisites
- Python 3.11 or higher
- Docker and Docker Compose
- Access to a Proxmox VE server
- Proxmox API credentials
Installation
- Clone the repository
- Copy
.env.exampleto.envand update with your Proxmox credentials:cp .env.example .env - Update the .env file with your Proxmox credentials:
PROXMOX_HOST=your_proxmox_host PROXMOX_USER=your_proxmox_user@pam PROXMOX_PASSWORD=your_proxmox_password PROXMOX_VERIFY_SSL=false
Running with Docker Compose
-
Build and start the container:
docker-compose up --build -
The server will be available at
http://localhost:8008
API Endpoints
The MCP server provides the following context endpoints:
get_cluster_info: Returns general information about the Proxmox clusterget_node_info: Returns detailed information about a specific Proxmox nodeget_vm_info: Returns detailed information about a specific VMlist_vms: Returns a list of all VMs in the cluster
Development
To run the server locally for development:
-
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Run the server:
uvicorn src.main:app --reload
Contributing
- Fork the repository
- Create your feature branch:
git checkout -b feature/my-new-feature - Run tests and format code:
pytest black src/ tests/ flake8 src/ tests/ - Commit your changes:
git commit -am 'Add some feature' - Push to the branch:
git push origin feature/my-new-feature - Submit a merge request
Development Guidelines
- Follow PEP 8 style guide
- Write tests for new features
- Update documentation when necessary
- Use type hints
- Write clear commit messages
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.