kubectl-mcp-server and mcp-kubernetes
These are competitors offering similar MCP server implementations for Kubernetes cluster interaction, with the first being more mature and widely adopted (847 vs 51 stars) while the second is an official Azure effort that may provide enterprise-focused features or tighter integration with Azure Kubernetes Service.
About kubectl-mcp-server
rohitg00/kubectl-mcp-server
A Model Context Protocol (MCP) server for Kubernetes. Install: npx kubectl-mcp-server or pip install kubectl-mcp-server
Exposes 253 Kubernetes tools through MCP's transport layer, enabling AI assistants to perform diagnostics, deployments, and cost optimization via natural language rather than imperative commands. Supports multi-cluster management, interactive HTML dashboards, and non-destructive mode with OAuth 2.1 authentication for enterprise deployments. Integrates with Claude, Cursor, Windsurf, Copilot and 15+ AI platforms through standardized MCP protocol.
About mcp-kubernetes
Azure/mcp-kubernetes
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes
Implements a unified `call_kubectl` tool that consolidates operations into a single interface (reducing context overhead compared to legacy multi-tool approaches), while supporting role-based access control through `readonly`, `readwrite`, and `admin` modes that filter operations at registration time. Integrates with kubectl and optional ecosystem tools (Helm, Cilium, Hubble), communicating via stdio transport by default and supporting OpenTelemetry tracing for observability.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work