# Lumino MCP Server

An MCP server for AI-assisted observability across Kubernetes, OpenShift, and Tekton. Use it to inspect logs, events, resources, and failed pipelines.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11
- Author: spre-sre
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/spre-sre/lumino-mcp-server
- Updated: 2026-09-04
- HTML: https://affpapa.org/en/nevibecode/mcp/lumino-mcp-server

## What it does

Lumino MCP Server gives an AI assistant access to Kubernetes and OpenShift diagnostics. It can inspect namespaces, pods, resources, and label-based searches, while also checking OpenShift operators and analyzing etcd logs.

Its Tekton tools monitor pipeline and task runs, retrieve logs, trace activity across clusters, and investigate failed runs. The server also supports log summaries, anomaly detection, resource bottleneck forecasts, certificate checks, and what-if analysis for configuration changes.

You need Python 3.10+, an MCP client, and read access to a Kubernetes or OpenShift cluster. The setup uses `KUBECONFIG`; without a valid kubeconfig, cluster operations cannot work. In Claude Code, add it with `claude mcp add lumino -- uvx lumino-mcp-server`.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `KUBECONFIG` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env KUBECONFIG=<KUBECONFIG> --transport stdio lumino-mcp-server -- uvx lumino-mcp-server
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from lumino-mcp-server <command>

### Codex

**Platform CLI**
```bash
codex mcp add lumino-mcp-server --env KUBECONFIG=<KUBECONFIG> -- uvx lumino-mcp-server
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from lumino-mcp-server <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "lumino-mcp-server": {
            "command": "uvx",
            "args": [
                "lumino-mcp-server"
            ],
            "env": {
                "KUBECONFIG": "<KUBECONFIG>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from lumino-mcp-server <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "lumino-mcp-server": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "lumino-mcp-server"
            ],
            "env": {
                "KUBECONFIG": "<KUBECONFIG>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from lumino-mcp-server <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e KUBECONFIG=<KUBECONFIG> lumino-mcp-server uvx lumino-mcp-server
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from lumino-mcp-server <command>

## When to use it
- inspect Kubernetes cluster health
- trace the cause of a failed Tekton pipeline
- retrieve logs and events for a troubled pod
- test the impact of a configuration change
- check TLS certificate expiry and issues

## Example prompts
- List all namespaces in my Kubernetes cluster.
- Investigate the latest failed Tekton pipeline and explain the likely cause.
- Review the events and logs for the pod that keeps restarting.

## Similar
- [kubernetes-mcp-server](https://affpapa.org/en/nevibecode/mcp/kubernetes-mcp-server.md) — MCP server · ★ 2186
- [openshift](https://affpapa.org/en/nevibecode/skills/openshift.md) — skill · 349 installs
- [ai-sre-incident-response](https://affpapa.org/en/nevibecode/skills/ai-sre-incident-response.md) — skill · 328 installs
- [axiom-sre](https://affpapa.org/en/nevibecode/skills/axiom-sre.md) — skill · 5100 installs
- [observability-sre-triage](https://affpapa.org/en/nevibecode/skills/observability-sre-triage.md) — skill · 1000 installs
- [observability-engineer](https://affpapa.org/en/nevibecode/skills/observability-engineer.md) — skill · 93 installs

---
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