Kubernetes
This Kubernetes MCP server by Thanhdeptr provides cluster management capabilities through kubectl and Helm integration, featuring both read-only and destructive operations with configurable safety modes. Built with TypeScript using the official Kubernetes client-node library and supporting multiple transport methods including stdio and SSE, it offers comprehensive kubectl operations (get, describe, apply, delete, create, logs, patch, rollout, scale), Helm chart management, port forwarding, pod command execution, and context switching across multiple clusters. The implementation includes resource tracking for cleanup operations, container templates for quick deployments, diagnostic prompts for troubleshooting workflows, and Docker containerization with support for GKE, EKS, and local clusters, making it valuable for DevOps engineers managing Kubernetes infrastructure, developers debugging applications, and teams automating deployment pipelines through AI-assisted cluster operations.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/thanhdeptr/k8s-aiassistant
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Kubernetes from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.