Kubernetes AI Assistant
Kubernetes AI Assistant MCP server by Thanhdeptr that combines MCP Server for Kubernetes management with Rancher UI extensions to provide comprehensive cluster operations through kubectl and Helm integration. The implementation offers both read-only and destructive operations with configurable filtering, supporting unified kubectl commands for resource management (get, describe, apply, delete, create), Helm chart operations, port forwarding, scaling, rollouts, and specialized diagnostic capabilities through a k8s-diagnose prompt that guides systematic troubleshooting workflows. Built with TypeScript and featuring resource tracking, context switching, and transport flexibility (stdio/SSE), it serves DevOps teams managing Kubernetes clusters, developers needing programmatic access to cluster operations, and AI assistants requiring structured approaches to Kubernetes diagnostics and resource management with safety controls for production environments.
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_ai_assistant_mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Kubernetes AI Assistant 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.