
mcp-nutanix
MCP Server for Nutanix Prism Central
README
MCP Nutanix
A Model Context Protocol (MCP) server for interacting with Nutanix Prism Central APIs through Large Language Models (LLMs).
⚠️ Disclaimer
THIS IS AN EXPERIMENTAL PROJECT
This project was created as a personal project to explore the capabilities of the Model Context Protocol frameworks in Go. It is:
- NOT an official Nutanix product or tool
- NOT supported, endorsed, or maintained by Nutanix
- NOT suitable for production environments
- PROVIDED AS-IS with no warranties or guarantees
USE AT YOUR OWN RISK: The author takes no responsibility for any issues, damages, or outages that may result from using this code.
Overview
This MCP server allows LLMs to interact with Nutanix Prism Central by:
- Connecting to a Prism Central instance with user credentials
- Listing various resources (VMs, Clusters, Hosts, etc.)
- Retrieving specific resource details via URI-based access
The implementation uses the Prism Go Client to communicate with Prism Central and the MCP Go library to implement the Model Context Protocol.
Getting Started
Prerequisites
- Go 1.23 or higher
- Access to a Nutanix Prism Central instance
- Tools like
make
andgo fmt
for building
Building
# Clone the repository
git clone https://github.com/thunderboltsid/mcp-nutanix.git
cd mcp-nutanix
# Build the MCP server
make build
Running
./bin/mcp-nutanix
The server will start and prompt for Prism Central credentials.
Usage
Once the MCP server is running and connected to your Prism Central instance, LLMs can interact with it through the MCP protocol.
Resource Listing
To list resources, use the appropriate tool:
vms
clusters
hosts
images
subnets
The LLM will receive a JSON list of resources that it can parse and analyze.
Resource Access
To access a specific resource, use a resource URI:
vm://{uuid}
cluster://{uuid}
host://{uuid}
The LLM will receive detailed JSON information about the specific resource.
Development
Project Structure
mcp-nutanix/
├── bin/ # Compiled binaries
├── internal/ # Internal packages
│ ├── client/ # Prism Central client handling
│ ├── codegen/ # Code generation utilities
│ └── json/ # JSON helpers
├── pkg/ # components
│ ├── prompts/ # MCP prompt implementations
│ ├── resources/ # Resource handlers
│ └── tools/ # Tool handlers
└── Makefile # Build and utility commands
Code Generation
The project uses code generation to create resource and tool handlers. To update these:
make generate
Limitations
- Response size is limited by the MCP protocol
- Some resources with large response sizes may cause errors
- No pagination support in the current implementation
- Only supports read operations, no create/update/delete
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Nutanix for creating the Prism API
- Mark3Labs for the MCP Go library
- Nutanix Cloud Native for the Prism Go Client
Contributing
This is an experimental project with no formal contribution process. Feel free to create issues or pull requests.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.