Kubernetes
MCP-K8s-Server is a Kotlin-based server that provides AI assistants with direct access to Kubernetes cluster management capabilities. Developed by Hari Ohm Prasath, it exposes a comprehensive set of tools for monitoring and managing Kubernetes resources including pods, deployments, services, storage, networking, and Helm releases. The server connects to Kubernetes clusters using the local kubeconfig file and leverages the official Kubernetes Java client to interact with the API server. Particularly valuable for DevOps engineers and platform administrators who need to diagnose cluster issues, analyze resource utilization, and manage deployments through natural language interactions without switching to kubectl or other management tools.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/hariohmprasath/k8s-ai
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
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.