The k8s-pilot server provides a centralized control plane for managing multiple Kubernetes clusters with comprehensive operations on various resources.
Multi-Cluster Management: List clusters, switch between contexts, and perform cluster-aware operations
Resource Management: CRUD operations on Deployments, Services, Pods, ConfigMaps, Secrets, Ingresses, StatefulSets, DaemonSets, Roles, ClusterRoles, PersistentVolumes, Claims, ReplicaSets, and ServiceAccounts
Namespace Operations: Create/delete namespaces, manage labels, set resource quotas, and list resources
Node Management: View node details, manage labels and taints, cordon/uncordon nodes, and list pods per node
Monitoring: Fetch logs for pods (with container specification and tailing options) and inspect detailed resource information
Enables management of multiple Kubernetes clusters simultaneously, including CRUD operations on common resources like Deployments, Services, Pods, ConfigMaps, Secrets, Ingresses, StatefulSets, DaemonSets, Roles, and PersistentVolumes, as well as namespace and node management operations.
Supports creating and managing NGINX deployments within Kubernetes clusters, including setting up NGINX containers and connecting them to services.
Enables operations within the PyPy namespace in Kubernetes clusters, allowing resource deployment and management specific to this namespace.
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., "@k8s-pilot list all pods in the production namespace across all clusters"
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.
The Central Pilot for Your Kubernetes Fleets βοΈβοΈ
k8s_pilot is a lightweight, centralized control plane server for managing multiple Kubernetes clusters at once.
With powerful tools and intuitive APIs, you can observe and control all your clusters from one cockpit.
π Supports multi-cluster context switching
π§ Enables CRUD operations on most common Kubernetes resources
π Readonly mode for safe cluster inspection
βοΈ Powered by MCP for Claude AI and beyond
π Streamable HTTP transport support for remote access
π€ MCP Prompts for guided operations
π Context-aware logging for write operations
Related MCP server: Multi-Cluster MCP Server
Python 3.13 or higher
uv package manager
Access to Kubernetes clusters (~/.kube/config or in-cluster config)
# Install uv (if not installed)
# For MacOS
brew install uv
# For Linux
curl -LsSf https://astral.sh/uv/install.sh | sh# Clone the repository
git clone https://github.com/bourbonkk/k8s-pilot.git
cd k8s-pilot
# Launch with uv + MCP
uv run --with "mcp[cli]>=1.28.0,<2" python k8s_pilot.pyStreamable HTTP Transport: Remote cluster management via HTTP (in addition to stdio)
MCP Prompts: Built-in prompt templates for common K8s operations
Context-aware Logging: Write operations now report progress via MCP context
Bug Fixes: Fixed missing API clients for Ingress and RBAC resources
Security: Added readonly checks for node modification operations
Dockerfile: Modernized with uv package manager for faster builds
# Start with full read/write access
uv run --with "mcp[cli]>=1.28.0,<2" python k8s_pilot.py# Start in readonly mode - only read operations allowed
uv run --with "mcp[cli]>=1.28.0,<2" python k8s_pilot.py --readonly# Start with Streamable HTTP transport for remote access
uv run --with "mcp[cli]>=1.28.0,<2" python k8s_pilot.py --transport streamable-http# Show help
uv run --with "mcp[cli]>=1.28.0,<2" python k8s_pilot.py --helpYou can run k8s-pilot directly using the published Docker image without installing uv locally.
Make sure to mount your ~/.kube/config so the container can access your clusters.
docker run -i --rm \
-v ~/.kube/config:/root/.kube/config \
ghcr.io/bourbonkk/k8s-pilot:latestThe --readonly flag enables a safety mode that prevents any write operations to your Kubernetes clusters. This is perfect for:
Cluster inspection without risk of accidental changes
Audit scenarios where you need to view but not modify
Learning environments where you want to explore safely
Production monitoring with zero risk of modifications
pod_create, pod_update, pod_delete
deployment_create, deployment_update, deployment_delete
service_create, service_update, service_delete
configmap_create, configmap_update, configmap_delete
secret_create, secret_update, secret_delete
namespace_create, namespace_delete
All other create/update/delete operations
pod_list, pod_detail, pod_logs
deployment_list, deployment_get
service_list, service_get
configmap_list, configmap_get
secret_list, secret_get
namespace_list, namespace_get
All other list/get operations
k8s-pilot includes built-in prompt templates for common operations:
Prompt | Description |
| Step-by-step pod troubleshooting guide |
| Guided application deployment workflow |
| Comprehensive cluster health assessment |
| Safe namespace cleanup procedure |
Use this config to run k8s_pilot MCP server from within Claude:
{
"mcpServers": {
"k8s_pilot": {
"command": "uv",
"args": [
"--directory",
"<path-to-cloned-repo>/k8s-pilot",
"run",
"--with",
"mcp[cli]>=1.28.0,<2",
"python",
"k8s_pilot.py"
]
}
}
}For readonly mode, use this configuration:
{
"mcpServers": {
"k8s_pilot_readonly": {
"command": "uv",
"args": [
"--directory",
"<path-to-cloned-repo>/k8s-pilot",
"run",
"--with",
"mcp[cli]>=1.28.0,<2",
"python",
"k8s_pilot.py",
"--readonly"
]
}
}
}For Docker, use this configuration (replace YOUR_USERNAME with your actual Mac user name):
{
"mcpServers": {
"k8s_pilot_docker": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/Users/YOUR_USERNAME/.kube/config:/root/.kube/config",
"ghcr.io/bourbonkk/k8s-pilot:latest"
]
}
}
}Replace <path-to-cloned-repo> with the actual directory where you cloned the repo.
Create a Deployment using the nginx:latest image in the pypy namespace, and also create a Service that connects to it.
Seamlessly interact with multiple Kubernetes clusters
Perform context-aware operations
Easily switch between clusters via MCP prompts
View, create, update, delete:
Deployments, Services, Pods
ConfigMaps, Secrets, Ingresses
StatefulSets, DaemonSets
Roles, ClusterRoles
PersistentVolumes & Claims
Create/delete namespaces
List all resources in a namespace
Manage labels and resource quotas
View node details and conditions
Cordon/uncordon, label/taint nodes
List pods per node
This project is licensed under the MIT License. See the LICENSE file for details.
Add or update a label on a namespace.
Args: context_name: The Kubernetes context name namespace: The name of the namespace label_key: The label key to add label_value: The label value to set
Returns: JSON string containing the updated namespace labels
Inputs: label_key (required), namespace (required), label_value (required), context_name (required).
Add or update a label to a node.
Args: context_name: The Kubernetes context name node_name: The name of the node to modify label_key: The label key to add label_value: The label value to set
Returns: JSON string containing the updated node labels
Inputs: label_key (required), node_name (required), label_value (required), context_name (required).
Create a ClusterRole in the cluster.
Args: context_name: The Kubernetes context name name: The ClusterRole name rules: List of policy rules
Returns: Status of the creation operation
Inputs: name (required), rules (required), context_name (required).
Delete a ClusterRole from the cluster.
Args: context_name: The Kubernetes context name name: The ClusterRole name
Returns: Status of the deletion operation
Inputs: name (required), context_name (required).
Get details of a specific ClusterRole.
Args: context_name: The Kubernetes context name name: The ClusterRole name
Returns: Detailed information about the ClusterRole
Inputs: name (required), context_name (required).
List all ClusterRoles in the cluster.
Args: context_name: The Kubernetes context name
Returns: List of ClusterRole basic information
Inputs: context_name (required).
Create a ConfigMap in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ConfigMap name data: The data to store in the ConfigMap
Returns: Status of the creation operation
Inputs: data (required), name (required), namespace (required), context_name (required).
Delete a ConfigMap from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ConfigMap name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Get details of a specific ConfigMap.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ConfigMap name
Returns: Detailed information about the ConfigMap
Inputs: name (required), namespace (required), context_name (required).
List all ConfigMaps in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of ConfigMap basic information
Inputs: namespace (required), context_name (required).
Update an existing ConfigMap in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ConfigMap name data: The new data to update in the ConfigMap
Returns: Status of the update operation
Inputs: data (required), name (required), namespace (required), context_name (required).
Create a new namespace.
Args: context_name: The Kubernetes context name namespace: The name for the new namespace labels: Optional dictionary of labels to apply to the namespace
Returns: JSON string containing information about the created namespace
Inputs: namespace (required), context_name (required), labels.
Update an existing DaemonSet in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The DaemonSet name image: The new container image to update
Returns: Status of the update operation
Inputs: name (required), image (required), namespace (required), context_name (required).
Delete a namespace and all resources within it.
Args: context_name: The Kubernetes context name namespace: The name of the namespace to delete
Returns: JSON string containing the result of the operation
Inputs: namespace (required), context_name (required).
Delete a Deployment from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Deployment name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
List all Deployments in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of Deployment basic information
Inputs: namespace (required), context_name (required).
Update an existing Deployment in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Deployment name image: The new container image to update replicas: The new number of replicas
Returns: Status of the update operation
Inputs: name (required), image (required), replicas (required), namespace (required), +1 more.
Get all clusters from the kubeconfig file. :return:
Inputs: no named parameters.
Get the current cluster from the kubeconfig file. :return:
Inputs: no named parameters.
Get detailed information about a specific namespace.
Args: context_name: The Kubernetes context name namespace: The name of the namespace to get details for
Returns: JSON string containing detailed information about the namespace
Inputs: namespace (required), context_name (required).
Get detailed information about a specific node.
Args: context_name: The Kubernetes context name node_name: The name of the node to get details for
Returns: JSON string containing detailed information about the node
Inputs: node_name (required), context_name (required).
Create an Ingress in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Ingress name host: The host for the Ingress service_name: The backend service name service_port: The backend service port
Returns: Status of the creation operation
Inputs: host (required), name (required), namespace (required), context_name (required), +2 more.
Delete an Ingress from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Ingress name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Get details of a specific Ingress.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Ingress name
Returns: Detailed information about the Ingress
Inputs: name (required), namespace (required), context_name (required).
List all Ingresses in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of Ingress basic information
Inputs: namespace (required), context_name (required).
Update an existing Ingress in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Ingress name host: The new host for the Ingress service_name: The new backend service name service_port: The new backend service port
Returns: Status of the update operation
Inputs: host (required), name (required), namespace (required), context_name (required), +2 more.
List all namespaces in the Kubernetes cluster.
Args: context_name: The Kubernetes context name
Returns: JSON string containing basic information about all namespaces
Inputs: context_name (required).
List all nodes in the Kubernetes cluster.
Args: context_name: The Kubernetes context name
Returns: JSON string containing basic information about all nodes
Inputs: context_name (required).
Get details of a specific pod.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The pod name
Returns: Detailed information about the pod
Inputs: name (required), namespace (required), context_name (required).
Get logs from a pod or a specific container within the pod.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The pod name container: Optional container name (if pod has multiple containers) tail_lines: Number of lines to retrieve from the end of the logs previous: Whether to get logs from a previous instance of the container
Returns: Pod logs
Inputs: name (required), namespace (required), context_name (required), previous, +2 more.
Update an existing pod's metadata (only labels can be updated for an existing pod).
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The pod name labels: New labels to apply to the pod
Returns: Information about the updated pod
Inputs: name (required), namespace (required), context_name (required), labels.
Delete a PersistentVolumeClaim from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The PersistentVolumeClaim name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Get details of a specific PersistentVolumeClaim.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The PersistentVolumeClaim name
Returns: Detailed information about the PersistentVolumeClaim
Inputs: name (required), namespace (required), context_name (required).
List all PersistentVolumeClaims in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of PersistentVolumeClaim basic information
Inputs: namespace (required), context_name (required).
Create a PersistentVolume in the cluster.
Args: context_name: The Kubernetes context name name: The PersistentVolume name capacity: The storage capacity (e.g., "10Gi") access_modes: List of access modes (e.g., ["ReadWriteOnce"]) storage_class: The storage class name host_path: The host path for the volume
Returns: Status of the creation operation
Inputs: name (required), capacity (required), host_path (required), access_modes (required), +2 more.
Delete a PersistentVolume from the cluster.
Args: context_name: The Kubernetes context name name: The PersistentVolume name
Returns: Status of the deletion operation
Inputs: name (required), context_name (required).
Update an existing PersistentVolume's metadata (e.g., labels).
Args: context_name: The Kubernetes context name name: The PersistentVolume name labels: New labels to apply to the PersistentVolume
Returns: Status of the update operation
Inputs: name (required), labels (required), context_name (required).
Remove a label from a namespace.
Args: context_name: The Kubernetes context name namespace: The name of the namespace label_key: The label key to remove
Returns: JSON string containing the updated namespace labels
Inputs: label_key (required), namespace (required), context_name (required).
Remove a label from a node.
Args: context_name: The Kubernetes context name node_name: The name of the node to modify label_key: The label key to remove
Returns: JSON string containing the updated node labels
Inputs: label_key (required), node_name (required), context_name (required).
Remove a taint from a node.
Args: context_name: The Kubernetes context name node_name: The name of the node to modify taint_key: The taint key to remove
Returns: JSON string containing the updated node taints
Inputs: node_name (required), taint_key (required), context_name (required).
Create a ReplicaSet in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ReplicaSet name image: The container image to use replicas: Number of replicas labels: Labels to apply to the ReplicaSet
Returns: Status of the creation operation
Inputs: name (required), image (required), labels (required), replicas (required), +2 more.
Get details of a specific ReplicaSet.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The ReplicaSet name
Returns: Detailed information about the ReplicaSet
Inputs: name (required), namespace (required), context_name (required).
List all ReplicaSets in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of ReplicaSet basic information
Inputs: namespace (required), context_name (required).
Create a Role in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Role name rules: List of policy rules
Returns: Status of the creation operation
Inputs: name (required), rules (required), namespace (required), context_name (required).
Delete a Role from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Role name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Get details of a specific Role.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Role name
Returns: Detailed information about the Role
Inputs: name (required), namespace (required), context_name (required).
List all Roles in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of Role basic information
Inputs: namespace (required), context_name (required).
Create a Secret in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Secret name data: A dictionary of key-value pairs (values will be base64 encoded) secret_type: The type of the Secret (default is "Opaque")
Returns: Status of the creation operation
Inputs: data (required), name (required), namespace (required), context_name (required), +1 more.
Delete a Secret from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Secret name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
List all Secrets in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of Secret basic information
Inputs: namespace (required), context_name (required).
List all ServiceAccounts in a given namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace
Returns: List of ServiceAccount basic information
Inputs: namespace (required), context_name (required).
Create a Service in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Service name selector: A dictionary of labels to select the target pods ports: A list of ports (e.g., [{"port": 80, "target_port": 8080}]) service_type: The type of the Service (default is "ClusterIP")
Returns: Status of the creation operation
Inputs: name (required), ports (required), selector (required), namespace (required), +2 more.
Delete a Service from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Service name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Update an existing Service's metadata (e.g., labels).
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The Service name labels: New labels to apply to the Service
Returns: Status of the update operation
Inputs: name (required), labels (required), namespace (required), context_name (required).
Create a StatefulSet in the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The StatefulSet name image: The container image to use replicas: Number of replicas labels: Labels to apply to the StatefulSet
Returns: Status of the creation operation
Inputs: name (required), image (required), labels (required), replicas (required), +2 more.
Delete a StatefulSet from the specified namespace.
Args: context_name: The Kubernetes context name namespace: The Kubernetes namespace name: The StatefulSet name
Returns: Status of the deletion operation
Inputs: name (required), namespace (required), context_name (required).
Uncordon a node (mark as schedulable).
Args: context_name: The Kubernetes context name node_name: The name of the node to uncordon
Returns: JSON string containing the result of the operation
Inputs: node_name (required), context_name (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Scored across 57 tools
Each tool targets a distinct Kubernetes resource or operation (e.g., clusterrole_create vs clusterrole_delete, pod_logs vs pod_detail). There is no ambiguity between tools as they clearly differentiate by resource and action.
Tool names mix styles: some use verb_noun (e.g., create_namespace), others use noun_verb (e.g., configmap_create). Additionally, there are inconsistencies like plural vs singular (list_namespaces vs clusterrole_list). This makes naming unpredictable.
57 tools is high for a Kubernetes MCP server. While the scope is broad, many tools are redundant or could be combined (e.g., separate add/remove label tools for namespaces and nodes). The count exceeds typical ranges, but it is still manageable.
The server covers various resources but has notable gaps: missing deployment_create and deployment_get, no pod creation, no support for common resources like HPA, NetworkPolicy, or RBAC bindings. This limits its ability to perform complete workflows.
Deploy and operate Kubernetes: clusters, stacks, apps, logs, metrics and security, with OAuth.
Manage Kubernetes clusters, deployments, databases, secrets and observability on Mengi Cloud.
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 costsβall without needing to parse text output or use complex kubectl commands.
Deploy applications and manage governed Kubernetes preview spaces and capacity.
