News
Nutanix Launches MCP Server for AI-Driven Cloud Operations
Nutanix on Aug. 10 announced a Model Context Protocol (MCP) server for Nutanix Cloud Platform (NCP), giving AI assistants and developer tools a way to interact with infrastructure through the Nutanix Prism V4 API.
The open-source software is designed to act as a controlled layer between AI tools and Nutanix infrastructure. Nutanix specifically named GitHub Copilot, Claude Code and Cursor as examples of assistants that can use the server to translate natural-language requests into infrastructure API operations.
According to the Nutanix announcement, the MCP server is intended to let IT teams automate cloud-management tasks while continuing to apply existing security and access policies. Nutanix said potential uses include analyzing system health, surfacing diagnostics and preparing automation workflows while retaining human oversight.
The initial v0.8 release is a Technical Preview and is not designed or supported for production workloads, according to the project's release materials.
Security Controls Remain in Prism
The MCP server relies on the Nutanix Prism V4 API Gateway for execution, governance and security. Nutanix said connected AI tools can operate within the role-based permissions assigned to their Prism Central identities, rather than receiving unrestricted access to infrastructure.
The server uses read-only enforcement by default, blocking non-GET operations unless administrators explicitly enable write access. Nutanix also documents auditing of operations, along with throttling, metering and asynchronous task management for longer-running infrastructure actions.
"By creating a secure gateway between AI tools and our platform, we are giving customers the confidence to safely use AI to operate and govern their hybrid multicloud environments," said Thomas Cornely, executive vice president, Product Management, Nutanix.
The open-source MCP server repository says the software requires Python 3.11 or later and connects to Prism Central over its V4 APIs. It dynamically discovers the API namespaces available on the connected Prism Central deployment, allowing its available tools to reflect the platform version in use.
Nutanix said the server exposes more than 1,000 V4 API operations and can provide AI tools with API schemas, code samples and permission information. Developers can use that information to generate scripts in languages and formats including Python, Go, Java, JavaScript, PowerShell, curl and REST/JSON-compatible formats.
GitHub Copilot Among Supported Clients
For Microsoft-centric development teams, GitHub Copilot is among the AI assistants Nutanix explicitly identified as compatible with the MCP server. GitHub separately documents MCP support for Copilot Chat in environments including Visual Studio Code and Visual Studio.
GitHub says organizations using Copilot Business or Copilot Enterprise must enable the appropriate MCP policy before users can connect MCP servers through Copilot. Nutanix's current integration documentation provides detailed setup examples for tools including Cursor and Claude, while Nutanix-specific step-by-step GitHub Copilot configuration is Not documented.
The v0.8 release is available as open-source software. Nutanix also published a technical walkthrough showing example interactions with the server in non-production environments.
About the Author
David Ramel is an editor and writer at Converge 360.