Developer · Local MCP server
Kubeview
Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.mikhae1/kubeview- Version
- 2.0.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-09-28
- Updated
- 2026-09-28
- Publisher
- mikhae1 (GitHub)
- Listed under
- Kubernetes MCP servers
- Website
- github.com/mikhae1/kubeview-mcp
- Repository
- github.com/mikhae1/kubeview-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | kubeview-mcp | 2.0.2 | stdio |
How to connect Kubeview
Kubeview runs locally from a Node.js package published to the npm registry: kubeview-mcp version 2.0.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y kubeview-mcp@2.0.2. It reads these environment variables: KUBECONFIG, MCP_TRANSPORT, MCP_MODE, MCP_CODE_MODE_DISABLED_TOOLS, MCP_ARGO_TOOLS, MCP_ARGOCD_TOOLS, MCP_LOG_LEVEL, MCP_KUBE_CONTEXT, MCP_K8S_SKIP_TLS_VERIFY, MCP_HIDE_SENSITIVE, MCP_TIMEOUT, MCP_HTTP_HOST, MCP_HTTP_PORT, MCP_HTTP_PATH, MCP_HTTP_JSON_RESPONSE, MCP_APPROVAL_STATE_SECRET (secret), MCP_APPROVAL_REPLAY_DIR, MCP_ALLOWED_HOSTS, MCP_ALLOWED_ORIGINS and KUBE_MCP_FORCE_VM_SANDBOX; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"kubeview": {
"command": "npx",
"args": [
"-y",
"kubeview-mcp@2.0.2"
],
"env": {
"KUBECONFIG": "<value>",
"MCP_TRANSPORT": "<value>",
"MCP_MODE": "<value>",
"MCP_CODE_MODE_DISABLED_TOOLS": "<value>",
"MCP_ARGO_TOOLS": "<value>",
"MCP_ARGOCD_TOOLS": "<value>",
"MCP_LOG_LEVEL": "<value>",
"MCP_KUBE_CONTEXT": "<value>",
"MCP_K8S_SKIP_TLS_VERIFY": "<value>",
"MCP_HIDE_SENSITIVE": "<value>",
"MCP_TIMEOUT": "<value>",
"MCP_HTTP_HOST": "<value>",
"MCP_HTTP_PORT": "<value>",
"MCP_HTTP_PATH": "<value>",
"MCP_HTTP_JSON_RESPONSE": "<value>",
"MCP_APPROVAL_STATE_SECRET": "<secret>",
"MCP_APPROVAL_REPLAY_DIR": "<value>",
"MCP_ALLOWED_HOSTS": "<value>",
"MCP_ALLOWED_ORIGINS": "<value>",
"KUBE_MCP_FORCE_VM_SANDBOX": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Kubernetes Manifest AuditKube-linter audit for Kubernetes manifests — 63 checks: security, availability, RBAC, network. | Remote · HTTP |
| Kubernetes TroubleshootRead-only Kubernetes diagnostics: pods, logs, events, workloads, services, PVCs and nodes. | Local · stdio |
| kubeshark MCPReal-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS. | Local · stdio |
| KubeStellar MCPAI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP. | Local · stdio |
| KukGitRead and write KukGit repositories, files, issues and pull requests from an AI assistant. | Remote · HTTP |
| Kultur.devCultural Intelligence Infrastructure for AI Agents — 200+ markets, 15 tones, 8 tools. | Remote · SSE |
| Kvm PilotHands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited. | Local · stdio |
| L10n.dev - AI Localization AgentMCP Server that turns your AI agent into a localization expert with token-efficient i18n translation. | Local · stdio |