Nutanix launches MCP server to bring agentic AI to hybrid cloud operations

In summary

Nutanix has launched an open-source MCP server for Nutanix Cloud Platform, letting AI agents and developer tools automate hybrid multicloud operations securely.
The server connects tools such as GitHub Copilot, Claude Code and Cursor to NCP infrastructure via the Prism v4 API while enforcing existing security policies.
Architectural features include role-based access control, traffic throttling against agent swarm attacks, audit logging and human-in-the-loop oversight for long-running tasks.

Nutanix has launched a Model Context Protocol (MCP) server for its Nutanix Cloud Platform (NCP), giving enterprises a secure way to use AI agents and developer tools to automate hybrid multicloud operations.

The open-source software implements the MCP specification and connects AI tools - including GitHub Copilot, Claude Code and Cursor - to NCP infrastructure through the Nutanix Prism v4 API. It translates plain-English requests into API actions while automatically enforcing existing corporate security and access policies.

Key architectural features include role-based access control that confines agents to APIs for which they have explicit authorisation, built-in traffic throttling to prevent agent swarm attacks, comprehensive audit logging, and asynchronous task management for long-running operations. A "human-in-the-loop" capability keeps operator oversight in place.

For developers, the server provides AI coding assistants with system blueprints up front, allowing automated generation of platform-ready scripts in Python, Go, Java, JavaScript, PowerShell and REST/JSON-compatible formats.

"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 of product management at Nutanix.