Nutanix, a hybrid cloud infrastructure company, has released an open source Model Context Protocol (MCP) server for its cloud platform. The software connects external artificial intelligence assistants to enterprise infrastructure environments. By acting as a secure passthrough, the system translates plain English requests into infrastructure API actions for the Nutanix Cloud Platform.
Managing hybrid multicloud environments requires technical expertise and strict access controls. While artificial intelligence can expedite system upgrades and track network performance, IT teams need assurance that automated actions remain authorized. The MCP server addresses this requirement by connecting external tools such as GitHub Copilot, Claude Code and Cursor to the Nutanix Prism v4 API. This integration ensures that automated operations inherit existing corporate security policies and fine-grained access controls.
“Nutanix has a long history of using automation to simplify complex cloud operations. The MCP server is an exciting next step on our journey, allowing us to bring the power of autonomous AI agents to cloud management,” said Thomas Cornely, executive vice-president, Product Management, Nutanix. “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.”
The system relies on the Nutanix Prism V4 API Gateway to handle execution and governance. To secure operations, the gateway enforces role-based access control, limiting artificial intelligence agents to specific approved API calls. Built-in traffic regulation provides throttling and metering to prevent agent swarm attacks while tracking API usage across workflows. The platform also generates system logs to identify which agent initiated specific commands and offloads long-running operations as asynchronous tasks.
For software engineers, the release provides system blueprints that enable coding assistants to generate infrastructure scripts. Developers can output these platform-ready scripts in languages including Python, Java and Go, as well as JSON and REST-compatible formats. The server software, available for download on the company's developer portal, allows infrastructure teams to construct custom agents to manage their environments while maintaining human oversight over production changes.
