Nutanix MCP Server
Allows managing Nutanix virtual machines and cluster resources, including listing and creating images, creating VMs, collecting logs, and retrieving alerts via the Nutanix v4 API.
Click on "Install 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., "@Nutanix MCP Serverlist all virtual machines in my cluster"
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.
Nutanix MCP Server
A Model Context Protocol (MCP) server for Nutanix Virtual Machine Management APIs with a command-line chatbot interface.
Features
Nutanix v4 API client integration - Add a v4 APi client and create tools for your MCP server
LLM Provider Flexibility: Works with any Nutanix AI (NAI) LLM endpoint that follows OpenAI API standards (tested with llama-3-1-8b)
Dynamic Tool Integration: Tools are declared in the system prompt, ensuring maximum compatibility across different LLMs.
Server Configuration: Supports multiple MCP servers through a simple JSON configuration file like the Claude Desktop App.
Related MCP server: mcp-proxmox
Prerequisites
Python 3.8 or higher
Nutanix Prism Central credentials or API key
cluster UUID of PE cluster
Setup
Clone this repository:
git clone https://github.com/savrab/nutanix-mcp.git
cd nutanix-mcpCreate and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activateInstall dependencies:
pip install -r requirements.txtConfigure environment variables:
Copy
.env.exampleto.envFill in your Nutanix credentials in
.envAdd your NAI API key:
NAI_API_KEY=your_api_key_here
Configure MCP servers:
Update
servers_config.jsonwith your server configurationExample configuration:
{ "mcpServers": { "nutanix mcp server": { "command": "/path/to/python", "args": ["/path/to/nutanix_mcp_server.py"] } } }
Running the Application
Option 1: Run MCP Server Inspector to test your tools. Learn more about MCP inspector in this tutorial - https://modelcontextprotocol.io/docs/tools/inspector
Start the MCP server:
mcp dev nutanix_mcp_server.pyOption 2: After confirming your tools are running fine, you can start the chatbot or directly start the chatbot to use existing tools:
python mcp_chatbot.pyUsing the Chatbot
Initialization:
The chatbot will automatically initialize the MCP server
Available tools will be listed
System messages will be displayed
Chatting:
Type your message and press Enter
The chatbot will process your request
Tool execution progress will be shown
Results will be displayed in the terminal
Tool Usage:
Tools are automatically selected based on your request
Progress tracking is available for long-running operations
Error handling and retries are built-in
Exiting:
Type 'quit' or 'exit' to end the session
The chatbot will clean up resources properly
Currently Available MCP Tools
List Images
Lists all images available in the Nutanix cluster.
Create Image
Creates a new image in the Nutanix cluster.
Create VM
Creates an new VM based on the provided specs
Collect logs
Collects log for given time period and uploads it diamond server
Get Alerts
List the top 10 alerts on the PC
Environment Variables
Required environment variables:
NUTANIX_USERNAME: Your Nutanix usernameNUTANIX_PASSWORD: Your Nutanix passwordNUTANIX_PRISM_CENTRAL_URL: URL of your Prism Central instanceNAI_API_KEY: Your Nutanix AI API keyCLUSTER_UUID: Your PE cluster UUID
Troubleshooting
Server Connection Issues:
Verify server configuration in
servers_config.jsonCheck environment variables
Tool Execution Errors:
Verify that the tools are working fine using MCP inspector
Review execution logs
API Errors:
Verify API keys
Check the LLM endpoint on ai.nutanix.com
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/atalhens/ntnx-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server