# dot-ai

Connects coding agents to Kubernetes clusters to inspect workloads, diagnose outages, and draft rollout manifests. Built for platform and operations tasks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 338
- Author: vfarcic
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/vfarcic/dot-ai
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/dot-ai

## What it does

The server connects AI coding assistants directly to Kubernetes through the Model Context Protocol and the Vercel AI SDK. Assistants can query cluster health using ordinary language, track down the root cause of failing pods, and recommend deployment configurations. When troubleshooting operational incidents, the engine isolates raw cluster output from operator instructions to maintain a clear security boundary.

Beyond cluster diagnostics, the package runs semantic lookups across team documentation, validates organizational policies, and initializes repositories with governance files. The project holds beta status and records anonymous telemetry out of the box. Running it locally depends on Node.js and `npx`.

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

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add dot-ai -- npx -y @vfarcic/dot-ai
```

### Codex

**Platform CLI**
```bash
codex mcp add dot-ai -- npx -y @vfarcic/dot-ai
```

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add dot-ai npx -y @vfarcic/dot-ai
```

## When to use it
- Pinpoint root causes behind failing Kubernetes workloads
- Generate deployment parameters for new cluster services
- Search internal architecture and operations documentation
- Scaffold code repositories with standard governance files

## Example prompts
- Inspect the failing pods in staging and explain why the container crashed
- Recommend deployment manifest parameters for this background worker
- Search our platform documentation for ingress routing rules

## 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