Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
io.github.mikhae1/kubeview
https://github.com/mikhae1/kubeview-mcp
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Path to kubeconfig file; defaults to ~/.kube/config if unset.
Server mode: 'all' (default), 'code', or 'tools'. Controls which features are enabled.
Logging level: 'error', 'warn', 'info' (default), or 'debug'.
Kubernetes context name to use. If unset, uses the current context from kubeconfig.
Skip TLS certificate verification for Kubernetes API (use 'true' or '1'). Not recommended for production.
Enable global sensitive data masking. Set to 'true' or '1' to mask sensitive values in responses.
Default timeout in milliseconds for operations. If unset, uses plugin-specific defaults.
Disable Kubernetes plugin. Set to 'true' or '1' to disable.
Disable Helm plugin. Set to 'true' or '1' to disable.
Disable Argo Workflows plugin. Set to 'true' or '1' to disable.
Disable Argo CD plugin. Set to 'true' or '1' to disable.
Where to find authoritative docs and source for kubeview.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio