Provides comprehensive Kubernetes cluster management capabilities including listing and monitoring resources (pods, services, deployments, namespaces), viewing logs, describing pod details, getting cluster events, port-forwarding services, scaling deployments, and executing kubectl commands through natural language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Kubernetes MCP Server show me the logs for the nginx pod in the default namespace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A powerful MCP (Model Context Protocol) server for Kubernetes operations that allows you to manage your Kubernetes clusters using natural language through AI assistants.
� Resource Listing
List pods, services, deployments, and namespaces
Get detailed resource information
🔍 Monitoring & Debugging
View pod logs with customizable line counts
Describe pod details for troubleshooting
Get cluster events for debugging
⚡ Operations
Port-forward services to local ports
Scale deployments up or down
Execute kubectl commands through natural language
🎯 Developer Focused
Designed for common Kubernetes developer workflows
Easy to extend with additional tools
Comprehensive error handling
Related MCP server: Kube MCP
Tool | Description | Parameters |
| List pods in a namespace |
|
| List services in a namespace |
|
| List deployments in a namespace |
|
| List all namespaces | None |
| Get detailed pod information |
|
| Get pod logs |
|
| Port forward a service |
|
| Scale a deployment |
|
| Get cluster events |
|
Node.js v18+
kubectl installed and configured to access your cluster
@modelcontextprotocol/cli (optional, for testing)
# Verify kubectl works
kubectl get pods
# Install MCP CLI (optional)
npm install -g @modelcontextprotocol/cli# Clone or download this repository
cd kube-mcp
# Install dependencies
npm install
# Run tests to verify setup
node test.js# Start the MCP server
npm start
# Or run directly
node server.jsThe server runs on stdio transport and will output: Kubernetes MCP server running on stdio
Add to your claude_desktop_config.json:
{
"mcpServers": {
"kubernetes": {
"command": "node",
"args": ["/absolute/path/to/kube-mcp/server.js"]
}
}
}For clients that support MCP, configure them to connect to this server using:
Command: node
Args: ["/path/to/server.js"]
Transport: stdio
Once connected to an MCP-compatible client, you can use natural language like:
"List all pods in the default namespace"
"Show me the logs for the nginx pod"
"Port forward the web service on port 8080 to my local port 3000"
"Scale the api deployment to 3 replicas"
"What events happened recently in the kube-system namespace?"
Run the test script to verify everything is working:
node test.jsThis will check:
✅ kubectl availability
✅ Server syntax validation
✅ Server startup capability
✅ Cluster connectivity
To add new tools:
Add the tool definition to the tools array in server.js
Add a corresponding case in the CallToolRequestSchema handler
Implement the kubectl command and response formatting
Test with node test.js
This server executes kubectl commands on your system
Ensure your kubectl context is set to the correct cluster
Be cautious when scaling deployments or port-forwarding in production
Review all operations before execution
MIT License - feel free to modify and distribute
Contributions are welcome! Please feel free to submit issues and enhancement requests.
Restart your MCP-enabled client (Cursor AI, Claude Desktop, VS Code MCP extension, etc.)
Now you can issue natural commands like:
“Show me all pods in namespace payments”
“Port forward postgres service to local 5432”
“Get logs from api-pod”
Analyze resource usage across the cluster
Inputs: namespace.
Add or update annotations on a resource
Inputs: resource (required), name (required), annotations (required), namespace.
Get available API resources
Inputs: no named parameters.
Get available API versions
Inputs: no named parameters.
Apply a Kubernetes manifest from a file or URL
Inputs: file (required), namespace.
Get the status of an ArgoCD application
Inputs: app (required), namespace.
List ArgoCD applications
Inputs: namespace.
Check if the current user can perform an action
Inputs: verb (required), resource (required), namespace.
Get cluster information
Inputs: no named parameters.
Mark a node as unschedulable
Inputs: node (required).
Copy files to/from a pod
Inputs: pod (required), source (required), destination (required), namespace, +1 more.
Create a backup of cluster resources
Inputs: namespace, output.
Create an ephemeral debug container in a pod
Inputs: pod (required), image (required), name (required), namespace, +1 more.
Create a new namespace
Inputs: name (required).
Get the current kubectl context
Inputs: no named parameters.
Create a debug container in a pod
Inputs: pod (required), namespace, image.
Delete a Kubernetes resource
Inputs: resource (required), name (required), namespace.
Describe details of a Kubernetes configmap
Inputs: configmap (required), namespace.
Describe details of a Kubernetes deployment
Inputs: deployment (required), namespace.
Describe details of a Kubernetes node
Inputs: node (required).
Describe details of a Kubernetes pod
Inputs: pod (required), namespace.
Describe details of a Kubernetes secret
Inputs: secret (required), namespace.
Describe details of a Kubernetes service
Inputs: service (required), namespace.
Drain a node for maintenance
Inputs: node (required), force, ignore_daemonsets.
Execute a command in a pod container
Inputs: pod (required), command (required), namespace, container.
Get cluster-wide metrics
Inputs: no named parameters.
Get the data from a configmap
Inputs: configmap (required), namespace.
List all kubectl contexts
Inputs: no named parameters.
Get a custom resource definition
Inputs: name (required).
Get Kubernetes events for troubleshooting
Inputs: namespace.
Get logs from a Kubernetes pod
Inputs: pod (required), namespace, lines, follow, +1 more.
Get detailed metrics for a node
Inputs: node (required).
Get detailed metrics for a pod
Inputs: pod (required), namespace.
Get the data from a secret
Inputs: secret (required), namespace.
Install a Helm chart
Inputs: name (required), chart (required), namespace, values, +1 more.
List Helm releases
Inputs: namespace.
Get the status of a Helm release
Inputs: release (required), namespace.
Uninstall a Helm release
Inputs: name (required), namespace.
Upgrade a Helm release
Inputs: name (required), chart (required), namespace, values.
List Istio gateways
Inputs: namespace.
List Istio virtual services
Inputs: namespace.
Add or update labels on a resource
Inputs: resource (required), name (required), labels (required), namespace.
List all Kubernetes resources in a namespace
Inputs: namespace.
List Kubernetes cluster role bindings
Inputs: no named parameters.
List Kubernetes cluster roles
Inputs: no named parameters.
List Kubernetes configmaps in a namespace
Inputs: namespace.
List Kubernetes custom resource definitions
Inputs: no named parameters.
List Kubernetes cronjobs in a namespace
Inputs: namespace.
List Kubernetes deployments in a namespace
Inputs: namespace.
List Kubernetes endpoints in a namespace
Inputs: namespace.
List Kubernetes horizontal pod autoscalers in a namespace
Inputs: namespace.
List Kubernetes ingresses in a namespace
Inputs: namespace.
List Kubernetes jobs in a namespace
Inputs: namespace.
List Kubernetes limit ranges in a namespace
Inputs: namespace.
List all Kubernetes namespaces
Inputs: no named parameters.
List Kubernetes network policies in a namespace
Inputs: namespace.
List all Kubernetes nodes
Inputs: no named parameters.
List Kubernetes pods in a namespace
Inputs: namespace.
List Kubernetes persistent volumes
Inputs: no named parameters.
List Kubernetes persistent volume claims in a namespace
Inputs: namespace.
List Kubernetes resource quotas in a namespace
Inputs: namespace.
List Kubernetes role bindings in a namespace
Inputs: namespace.
List Kubernetes roles in a namespace
Inputs: namespace.
List Kubernetes secrets in a namespace
Inputs: namespace.
List Kubernetes service accounts in a namespace
Inputs: namespace.
List Kubernetes services in a namespace
Inputs: namespace.
Patch a Kubernetes resource
Inputs: resource (required), name (required), patch (required), type, +1 more.
Port forward a Kubernetes service to a local port
Inputs: service (required), localPort (required), targetPort (required), namespace.
Port forward a Kubernetes pod to a local port
Inputs: pod (required), localPort (required), targetPort (required), namespace.
Show the rollout history of a deployment
Inputs: deployment (required), namespace.
Restart a deployment by triggering a rollout
Inputs: deployment (required), namespace.
Check the rollout status of a deployment
Inputs: deployment (required), namespace.
Run a pod with a specific image
Inputs: name (required), image (required), namespace, command.
Scale a Kubernetes deployment to a specified number of replicas
Inputs: deployment (required), replicas (required), namespace.
Update the image of a deployment
Inputs: deployment (required), container (required), image (required), namespace.
Show resource usage for nodes
Inputs: no named parameters.
Show resource usage for pods
Inputs: namespace.
Mark a node as schedulable
Inputs: node (required).
Switch to a different kubectl context
Inputs: context (required).
Get Kubernetes version information
Inputs: no named parameters.
Wait for a condition on a resource
Inputs: resource (required), name (required), condition (required), namespace, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 81 tools
Most tools have distinct purposes targeting specific resources and actions, but there is some overlap. For example, 'debug-pod' and 'create-ephemeral-container' both relate to pod debugging, and 'port-forward' vs 'port-forward-pod' could be confusing without careful reading of descriptions. However, the majority are well-differentiated.
The naming follows a consistent kebab-case verb-noun pattern throughout, with clear conventions like 'list-*', 'get-*', 'describe-*', and action-specific verbs. Minor deviations exist, such as 'cp' (abbreviation) and 'run' (single word), but overall the pattern is predictable and readable.
With 81 tools, the count is excessive for an MCP server, making it overwhelming and difficult for agents to navigate. While Kubernetes is a complex domain, this many tools suggests poor scoping and could lead to confusion or inefficiency in tool selection.
The toolset provides comprehensive coverage of Kubernetes operations, including CRUD, monitoring, debugging, and management tasks across resources. It supports core workflows like deployment, scaling, logging, and troubleshooting, with no apparent gaps for the domain.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Manage Rackspace Spot Kubernetes Cloudspaces, node pools, and VMs from your AI assistant.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
