k8s AIops is a Model Context Protocol (MCP) server: Governed Kubernetes ops — 55 MCP tools with audit, budget, undo, risk-tier audit labels. In practice that means any MCP-compatible AI assistant can call k8s AIops's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the Python package k8s-aiops (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.12.0, published under the MIT license, with source at AIops-tools/K8s-AIops on GitHub.
k8s AIops is listed under Cloud Service on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain k8s AIops for AIops-tools, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸PyPI package — k8s-aiops · MCP over stdio
▸Open source — MIT license · AIops-tools/K8s-AIops