# kubeleash

> kubeleash — kubeleash-kubeleash. Use this tool when you need to secure your Kubernetes cluster from over-privileged AI agents, providing a local policy-gated server with RBAC-style access control to prevent unintended actions. It solves the problem of safeguarding production environments from potential AI agent mistakes by limiting their access to sensitive resources. With kubeleash, you can input a kubeconfig file and output controlled, context-scoped access to your cluster.

Canonical page: https://skillsregistry.net/skills/kubeleash-kubeleash  
JSON: https://api.skillsregistry.net/v1/skills/kubeleash-kubeleash

## Description

Guardrails for AI agents on your cluster: a local, policy-gated Kubernetes MCP server with RBAC-style, context-scoped access control. Point it at an over-privileged kubeconfig — it still can't nuke prod.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** cloud-infra
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/kubeleash/kubeleash)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kubeleash-kubeleash"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kubeleash-kubeleash` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kubeleash-kubeleash/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt