# kubently

Troubleshoots Kubernetes clusters using natural language prompts. Investigates crashing pods, checks fleet health, and inspects logs straight from your coding agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 46
- Author: kubently
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/kubently/kubently
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/kubently

## What it does

Kubently bridges Kubernetes infrastructure with AI assistants using the Model Context Protocol. It investigates failing workloads, scans logs, and pinpoints root causes across multiple clusters simultaneously. Executors connect to the central service using outbound requests. Because of this design, you do not need public ingress or shared kubeconfig files.

The architecture relies on Redis for conversation context and coordinates tasks via the A2A protocol. Beyond interactive diagnostics, the system handles Alertmanager webhooks, verifies rollout health, and posts automated Slack digests. Operation requires an active API token for Anthropic, OpenAI, or Google. Deployment depends on Helm and a functional cluster running Kubernetes 1.28 or newer.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add kubently -- npx -y @kubently/cli
```

### Codex

**Platform CLI**
```bash
codex mcp add kubently -- npx -y @kubently/cli
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "kubently": {
            "command": "npx",
            "args": [
                "-y",
                "@kubently/cli"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "kubently": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@kubently/cli"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add kubently npx -y @kubently/cli
```

## When to use it
- diagnose crashlooping pods from events and workload logs
- troubleshoot firewalled clusters across a multi-cluster fleet
- verify workload health following a fresh deployment
- triage firing Alertmanager notifications automatically

## Example prompts
- Use kubently to investigate why checkout pods are restarting in prod
- Check all clusters via kubently for PVC storage exceeding 85 percent

## Similar
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [Oh My Posh Validator](https://affpapa.org/en/nevibecode/mcp/oh-my-posh-validator.md) — MCP server · ★ 23643
- [Keploy](https://affpapa.org/en/nevibecode/mcp/keploy.md) — MCP server · ★ 18727
- [Coder](https://affpapa.org/en/nevibecode/mcp/coder.md) — MCP server · ★ 17160
- [mcp](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — MCP server · ★ 12109

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md