kubestellar/kubestellar-mcp
Developer toolsЭта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал
AI-powered kubectl plugin for multi-cluster Kubernetes management
Обзор
AI-powered multi-cluster Kubernetes tools for Claude Code. kubestellar-mcp is the AI entry point to the — a CNCF Sandbox ecosystem for multi-cluster Kubernetes orchestration. kubestellar-mcp lets AI agents inspect and operate clusters through natural language. For visual dashboards and AI missions, see KubeStellar Console. Additional documentation lives in docs/: - docs/index.md - expanded setup, plugin workflow, CLI usage, and operational guidance - docs/ARCHITECTURE.md - architecture overview and contributor guide for the two MCP servers, request lifecycle, and how to add new tools If you are contributing new MCP capabilities, start with docs/ARCHITECTURE.md; it is the best guide to how the servers are organized and where new tools should be added. - docs/slo.
README
Показан фрагмент оригинального README. Открыть оригинал.
kubestellar-mcp
AI-powered multi-cluster Kubernetes tools for Claude Code.
Single-cluster UX for multi-cluster reality - work with your apps, not your clusters.
Why KubeStellar
kubestellar-mcp is the AI entry point to the KubeStellar platform — a CNCF Sandbox ecosystem for multi-cluster Kubernetes orchestration.
| Sub-project | Role |
|---|---|
| kubestellar | Core engine — BindingPolicy, WDS, ITS, WEC workload propagation |
| console | Web dashboard — 300+ cards, AI missions, GPU and LLM-d monitoring |
| console-marketplace | 153+ community card presets (GPU/AI/ML, ArgoCD, OPA, Falco, security) |
| console-kb | AI knowledge base — community missions and operational runbooks |
| kubestellar-mcp | This repo — MCP server for Claude, Cursor, Windsurf, VS Code |
kubestellar-mcp lets AI agents inspect and operate clusters through natural language. For visual dashboards and AI missions, see KubeStellar Console.
Components
| Binary | Description |
|---|---|
| kubestellar-ops | Multi-cluster diagnostics, RBAC analysis, security checks |
| kubestellar-deploy | App-centric deployment, GitOps, smart workload placement |
Documentation
Additional documentation lives in docs/:
docs/index.md- expanded setup, plugin workflow, CLI usage, and operational guidancedocs/ARCHITECTURE.md- architecture overview and contributor guide for the two MCP servers, request lifecycle, and how to add new tools
If you are contributing new MCP capabilities, start with docs/ARCHITECTURE.md; it is the best guide to how the servers are organized and where new tools should be added.
Operations
docs/slo.md- Service Level Objectives and Indicatorsdocs/alerts/- importable Prometheus alert rules aligned with the SLOsdocs/dashboards/- importable Grafana dashboardrunbooks/- operational runbooks (startup/shutdown, cluster discovery failures, credential rotation, connectivity loss, release rollback)docs/postmortem-template.md- incident postmortem templatedocs/severity-levels.md- P1-P4 incident severity scale used by the incident template and postmortem requirement
Installation
Homebrew (Recommended)
brew tap kubestellar/tap
# Install diagnostics tools
brew install kubestellar-ops
# Install deployment tools
brew install kubestellar-deploy
# Or install both
brew install kubestellar-ops kubestellar-deploy
From Releases
Установка
This server does not publish a one-line install command.
Open the repository installation guide Новичок в MCP? Начните с руководства на mcpskill.org →Конфигурация
{
"mcpServers": {
"kubestellar-ops": {
"command": "kubestellar-ops",
"args": ["--mcp-server"]
}
}
}