Skill of Skills
📄 skillStaleExperimentalhigh

k8s-mcp-server

by alexei-led

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

Supported Platforms

🤖 Claude Code

Stars

210

Skill Type

⚙️ Infrastructure Operations

Quality Score

70/200

License

MIT

Forks

39

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/alexei-led/k8s-mcp-server

Quality Breakdown

70/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
○Composability+15

Repo Health

○Recent Activity+15
○Scripts/Automation+10
○Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • CLI execution capabilities: repo enables Claude to execute Kubernetes CLI tools (kubectl, istioctl, helm, argocd) with potential cluster-wide impact
  • System command execution: cli_executor.py module suggests direct command execution capabilities without clear approval gates
  • Kubernetes cluster access: tool provides access to k8s cluster operations including deployments, scaling, config modifications
  • Persistent configuration file: CLAUDE.md indicates Claude-specific persistent configuration that could be modified autonomously
  • Docker containerization: Dockerfile and docker-compose.yml suggest container execution environment setup
  • No explicit human approval gates mentioned for destructive operations (scale, delete, apply manifests)