kubeview for Gemini CLI
io.github.mikhae1/kubeview
Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
client:Gemini CLI
transport:stdio
runtime:npm
Install kubeview in Gemini CLI
~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json
{
"mcpServers": {
"kubeview": {
"command": "npx",
"args": [
"-y",
"kubeview-mcp"
],
"env": {
"KUBECONFIG": "<KUBECONFIG>",
"MCP_TRANSPORT": "<MCP_TRANSPORT>",
"MCP_MODE": "<MCP_MODE>",
"MCP_CODE_MODE_DISABLED_TOOLS": "<MCP_CODE_MODE_DISABLED_TOOLS>",
"MCP_ARGO_TOOLS": "<MCP_ARGO_TOOLS>",
"MCP_ARGOCD_TOOLS": "<MCP_ARGOCD_TOOLS>",
"MCP_LOG_LEVEL": "<MCP_LOG_LEVEL>",
"MCP_KUBE_CONTEXT": "<MCP_KUBE_CONTEXT>",
"MCP_K8S_SKIP_TLS_VERIFY": "<MCP_K8S_SKIP_TLS_VERIFY>",
"MCP_HIDE_SENSITIVE": "<MCP_HIDE_SENSITIVE>",
"MCP_TIMEOUT": "<MCP_TIMEOUT>",
"MCP_HTTP_HOST": "<MCP_HTTP_HOST>",
"MCP_HTTP_PORT": "<MCP_HTTP_PORT>",
"MCP_HTTP_PATH": "<MCP_HTTP_PATH>",
"MCP_HTTP_JSON_RESPONSE": "<MCP_HTTP_JSON_RESPONSE>",
"MCP_APPROVAL_STATE_SECRET": "<MCP_APPROVAL_STATE_SECRET>",
"MCP_APPROVAL_REPLAY_DIR": "<MCP_APPROVAL_REPLAY_DIR>",
"MCP_ALLOWED_HOSTS": "<MCP_ALLOWED_HOSTS>",
"MCP_ALLOWED_ORIGINS": "<MCP_ALLOWED_ORIGINS>",
"KUBE_MCP_FORCE_VM_SANDBOX": "<KUBE_MCP_FORCE_VM_SANDBOX>",
"MCP_DISABLE_KUBERNETES_PLUGIN": "<MCP_DISABLE_KUBERNETES_PLUGIN>",
"MCP_DISABLE_HELM_PLUGIN": "<MCP_DISABLE_HELM_PLUGIN>",
"MCP_DISABLE_ARGO_PLUGIN": "<MCP_DISABLE_ARGO_PLUGIN>",
"MCP_DISABLE_ARGOCD_PLUGIN": "<MCP_DISABLE_ARGOCD_PLUGIN>"
}
}
}
}Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs