Community MCP server for Kubernetes cluster operations.
npx -y @mcp-community/server-kubernetes
{
"mcpServers": {
"kubernetes": {
"args": [
"-y",
"@mcp-community/server-kubernetes"
],
"command": "npx"
}
}
}Apply a Kubernetes manifest
{
"type": "object",
"required": [
"manifest"
],
"properties": {
"manifest": {
"type": "string"
}
}
}// Input
{
"manifest": "apiVersion: v1\\nkind: Pod..."
}// Output
{
"resources": [
{
"kind": "Pod",
"name": "web",
"action": "created"
}
]
}Get logs from a pod
{
"type": "object",
"required": [
"pod",
"namespace"
],
"properties": {
"pod": {
"type": "string"
},
"tail": {
"type": "integer"
},
"namespace": {
"type": "string"
}
}
}// Input
{
"pod": "web-abc",
"tail": 100,
"namespace": "default"
}// Output
{
"logs": "Starting server on :8080"
}List pods in a namespace
Community MCP server for Kubernetes cluster operations.
Kubernetes provides 4 tools including apply_manifest, get_logs, list_pods, and 1 more.
Yes, Kubernetes is completely free to use with no usage limits on the free tier.
You can install Kubernetes using the following command: npx -y @mcp-community/server-kubernetes. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
{
"type": "object",
"required": [
"namespace"
],
"properties": {
"namespace": {
"type": "string"
}
}
}// Input
{
"namespace": "default"
}// Output
{
"pods": [
{
"name": "web-abc",
"status": "Running",
"restarts": 0
}
]
}Scale a deployment
{
"type": "object",
"required": [
"name",
"replicas"
],
"properties": {
"name": {
"type": "string"
},
"replicas": {
"type": "integer"
},
"namespace": {
"type": "string"
}
}
}// Input
{
"name": "web",
"replicas": 3,
"namespace": "default"
}// Output
{
"replicas": 3
}Kubernetes is listed under the Development Tools category in the AgentForge MCP registry.
Kubernetes has a current uptime of 99.6% with an average response time of 150ms.
To connect Kubernetes, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Kubernetes's tools via the Model Context Protocol.