k8s-mcp-server and mcp-kubernetes

These are competitors offering similar MCP server implementations for Kubernetes access, with the alexei-led version having more community adoption (205 vs 51 stars) but both providing functionally overlapping bridges between AI assistants and Kubernetes clusters.

k8s-mcp-server
56
Established
mcp-kubernetes
51
Established
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 20/25
Maintenance 10/25
Adoption 8/25
Maturity 15/25
Community 18/25
Stars: 205
Forks: 37
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 51
Forks: 16
Downloads:
Commits (30d): 0
Language: Go
License: MIT
No Package No Dependents
No Package No Dependents

About k8s-mcp-server

alexei-led/k8s-mcp-server

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments

# Technical Summary Implements MCP via stdio, HTTP streamable, and SSE transports—with stdio as the Claude Desktop default—enabling bidirectional command execution without polling. Runs as a non-root containerized process with command validation and Unix tool piping (`jq`, `grep`, `sed`) for output processing, plus native cloud provider authentication for AWS EKS, GKE, and Azure AKS. Integrates directly into Claude Desktop through simple JSON configuration, allowing natural-language Kubernetes operations without leaving the interface.

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.

Scores updated daily from GitHub, PyPI, and npm data. How scores work