By rubixkube-io
RubixKube Site Reliability Intelligence for modern infrastructure: investigate incidents, review evidence-backed RCAs, and track remediation across Kubernetes, AWS, GCP, Linux VMs, and hybrid platforms.
List open infrastructure issues prioritized by severity. Use when the user asks what needs attention, wants to see current alerts, or is looking for problems in a specific environment, cloud account/project, VM estate, cluster, namespace, or project.
Complete health view of a specific RubixKube environment: infrastructure details, resource status, workload counts, active issues, and recent RCAs. Use when the user asks about a named environment, cloud project/account, VM estate, Kubernetes cluster, or specific cluster_id.
RubixKube platform overview and recent activity timeline. Use when the user asks about overall system status, what's happening in production, post-deploy checks, or wants a summary of recent incidents.
Deep investigation of a specific infrastructure issue. Use when the user asks why something is broken, wants to debug a service, pod, cloud resource, VM, or references an insight ID. Returns root cause, RCA findings, and linked remediation actions.
List open remediation action items with priority and linked incident context. Use when the user asks what to work on, wants to see their action queue, or is tracking remediation progress for an incident.
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Site Reliability Intelligence in your IDE and terminal.
Investigate incidents, review evidence-backed root cause analyses, and track remediation across Kubernetes, AWS, GCP, Linux VMs, and hybrid platforms — without leaving your editor.
Works with Claude Code and Cursor.
Ask questions in plain English and your assistant will pull live signal from your RubixKube tenant.
What's going on in prod right now?
Any critical alerts in the last 2 hours?
Why is the payment service crashing?
Show me the RCA for INSIGHT-abc123
What should I work on first?
Behind the scenes, the plugin loads 6 skills that route those questions to 7 MCP tools backed by your live cluster, cloud, and VM data.
Install from the marketplace:
Or add the MCP directly via .cursor/mcp.json:
{
"mcpServers": {
"rubixkube": {
"type": "http",
"url": "https://mcp.rubixkube.ai/mcp"
}
}
}
Install via the official marketplace:
/plugin install rubixkube
Or add this repo as a marketplace and install from it directly:
/plugin marketplace add rubixkube-io/rubixkube-for-ai
/plugin install rubixkube@rubixkube
Or add just the MCP server:
claude mcp add --transport http rubixkube https://mcp.rubixkube.ai/mcp
The first time you use a RubixKube tool, your editor opens a browser window to log in with your RubixKube account — the same login as console.rubixkube.ai. The session persists after the first sign-in.
| Tool | What it answers |
|---|---|
platform_status | Overall dashboard — environments, active issues by severity, RCA count, open actions |
active_issues | Prioritized list of open issues, filterable by environment, namespace, severity |
investigate | Deep dive — root cause + RCA + linked actions for a specific issue |
cluster_health | Full view of one connected environment — infra snapshot, workloads, issues, recent RCAs |
pending_actions | Open remediation tasks, filterable by environment, priority, status |
rca_details | Complete RCA report — root cause, contributing factors, remediation, rollback, evidence |
recent_activity | Timeline of recent insights, RCAs, and action updates |
When installed as a plugin, these skills guide your AI assistant on when and how to use each tool:
| Skill | Trigger phrases |
|---|---|
infra-status | "What's going on?", "How's prod?", "Post-deploy check", "Recent activity" |
active-issues | "What's broken?", "Any critical alerts?", "Open issues in project X" |
investigate | "Why is X broken?", "Investigate this error", "Debug the payment service" |
cluster-health | "How's prod?", "Check staging", "Status of environment X" |
pending-actions | "What should I work on?", "Show action items", "What's pending?" |
rca-report | "Show me the RCA", "Root cause analysis for X", "Full investigation report" |
https://mcp.rubixkube.aiMIT — see LICENSE.
npx claudepluginhub rubixkube-io/rubixkube-for-ai --plugin rubixkubeComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Production-grade vibe coding suite. Structured workflows from discovery to deployment: start, build, ship, fix, refactor.