Server Variance Authority

S.V.A. MCP server

Ask the SVA from your agent

  1. Add it to Claude CodeOne command. It is read-only and needs no key.
    claude mcp add --transport http sva https://your-sva-site/api/mcp
  2. Or any MCP clientCursor, VS Code, Windsurf and others take a remote HTTP server in their MCP config:
    {"mcpServers":{"sva":{"type":"http","url":"https://your-sva-site/api/mcp"}}}
  3. Ask it things“Pods are crash-looping in prod. Which read-only skills should I start with?” Your agent can call:
    • search_skills finds skills for an incident or task, with safety labels
    • get_skill a skill's full case file and install command
    • skills_for_incident skills per phase: detect, triage, mitigate, postmortem
    • get_runbook step-by-step handbooks, read-only steps first
    • get_stack stack bundles with one install command

All skills / Kubernetes

kubernetes-specialist

Destructive

Writes Kubernetes manifests, pod security settings, service accounts and Helm charts for new and existing workloads.

jeffallan/claude-skills/skills/kubernetes-specialistUnreviewed
Stars
★ 12k
Installs
14k
Last commit
License
MIT
Partner audits✓ Gen Agent Trust Hub · SAFE! Socket✓ Snyk · LOW✕ Runlayer · HIGH✓ ZeroLeaks

Installs and audits via skills.sh. Their audits are kept separate from our label.

Why this label

Label from the automated scanner. Not yet reviewed by a person.

Helps with

Phases

Mitigate

In stacks

Runbooks that use it

Install

npx skills add jeffallan/claude-skills --skill kubernetes-specialist

S.V.A. field guide

How to use kubernetes-specialist

  1. Install the skillRun this in your project. It adds the SKILL.md files where your agent looks for them.
    npx skills add jeffallan/claude-skills --skill kubernetes-specialist
  2. Reference it in your agentClaude Code, Codex, Cursor and other agents pick installed skills up on their own. To be sure, name it in your request:
    Use the kubernetes-specialist skill. Here is the task: …
  3. Put it to workHand it a real job and read what it plans before it runs anything. Check the risk label first: anything above read can change state.