An MCP (Model Context Protocol) server that provides powerful tools to interact with OpenShift/Kubernetes clusters using the openshift-python-wrapper library.

• Python 3.8+
• Access to an OpenShift/Kubernetes cluster
• Valid kubeconfig file

# Install with uv (recommended)
uv tool install openshift-python-wrapper

# Or install with pip
pip install openshift-python-wrapper

Once installed, you can run the MCP server with:

# Run the MCP server
openshift-mcp-server

For development or running from source:

# Clone and install in development mode
git clone https://github.com/RedHatQE/openshift-python-wrapper.git
cd openshift-python-wrapper

# Or run directly
uv run mcp_server/server.py

List Kubernetes/OpenShift resources with filtering capabilities.

Parameters:

• resource_type (required): Type of resource (e.g., "pod", "deployment")
• namespace (optional): Namespace to search in
• label_selector (optional): Filter by labels (e.g., "app=nginx")
• field_selector (optional): Filter by fields
• limit (optional): Maximum number of results

Example:

# List all pods in the default namespace
list_resources(resource_type="pod", namespace="default")

# List deployments with specific label
list_resources(resource_type="deployment", label_selector="app=frontend")

Get detailed information about a specific resource.

Parameters:

• resource_type (required): Type of resource
• name (required): Resource name
• namespace (optional): Namespace (required for namespaced resources)
• output_format (optional): Format - "info", "yaml", "json", "wide" (default: "info")

Example:

# Get pod details in YAML format
get_resource(resource_type="pod", name="nginx", namespace="default", output_format="yaml")

Create a new resource from YAML or specifications.

Parameters:

• resource_type (required): Type of resource
• name (required): Resource name
• namespace (optional): Namespace for namespaced resources
• yaml_content (optional): Complete YAML definition
• spec (optional): Resource specification as dict
• labels (optional): Labels to apply
• annotations (optional): Annotations to apply
• wait (optional): Wait for resource to be ready

Example:

# Create a namespace
create_resource(resource_type="namespace", name="test-ns", spec={})

# Create from YAML
yaml = """
apiVersion: v1
kind: Pod
metadata:
  name: nginx
spec:
  containers:
  - name: nginx
    image: nginx:latest
"""
create_resource(resource_type="pod", name="nginx", yaml_content=yaml)

Update an existing resource using patch operations.

Parameters:

• resource_type (required): Type of resource
• name (required): Resource name
• namespace (optional): Namespace
• patch (required): Patch data as dict
• patch_type (optional): "merge", "strategic", "json" (default: "merge")

Example:

# Scale a deployment
update_resource(
    resource_type="deployment",
    name="my-app",
    namespace="default",
    patch={"spec": {"replicas": 3}}
)

Delete a resource.

Parameters:

• resource_type (required): Type of resource
• name (required): Resource name
• namespace (optional): Namespace
• wait (optional): Wait for deletion to complete (default: true)
• timeout (optional): Deletion timeout in seconds (default: 60)

Example:

delete_resource(resource_type="pod", name="nginx", namespace="default")

Apply YAML manifests containing one or more resources.

Parameters:

• yaml_content (required): YAML content with one or more resources
• namespace (optional): Default namespace for resources without namespace

Example:

yaml_content = """
---
apiVersion: v1
kind: Namespace
metadata:
  name: test-app
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx
  namespace: test-app
spec:
  replicas: 2
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - name: nginx
        image: nginx:latest
"""
apply_yaml(yaml_content=yaml_content)

Retrieve logs from pod containers.

Parameters:

• name (required): Pod name
• namespace (required): Namespace
• container (optional): Container name (for multi-container pods)
• tail_lines (optional): Number of lines from end
• since_seconds (optional): Logs since N seconds ago
• previous (optional): Get logs from previous container instance

Example:

# Get last 100 lines of logs
get_pod_logs(name="my-app-abc123", namespace="production", tail_lines=100)

# Get logs from last hour
get_pod_logs(name="my-app-abc123", namespace="production", since_seconds=3600)

Execute commands inside pod containers.

Parameters:

• name (required): Pod name
• namespace (required): Namespace
• command (required): Command to execute as list
• container (optional): Container name

Example:

# Check nginx config
exec_in_pod(
    name="nginx-pod",
    namespace="default",
    command=["nginx", "-t"]
)

# List files
exec_in_pod(
    name="my-app",
    namespace="default",
    command=["ls", "-la", "/app"]
)

Get Kubernetes events related to a resource.

Parameters:

• resource_type (required): Type of resource
• name (required): Resource name
• namespace (optional): Namespace
• limit (optional): Maximum events to return (default: 10)

Example:

# Get pod events
get_resource_events(resource_type="pod", name="crashloop-pod", namespace="default")

Get all available resource types.

Parameters:

• random_string (required): Any string (required by MCP protocol)

Example:

get_resource_types(random_string="x")

Add to your Cursor settings (~/.cursor/mcp.json):

{
  "mcpServers": {
    "openshift-python-wrapper": {
      "command": "openshift-mcp-server"
    }
  }
}

Then use in Cursor with @openshift-python-wrapper.

Add to Claude Desktop config:

{
  "mcpServers": {
    "openshift-python-wrapper": {
      "command": "openshift-mcp-server"
    }
  }
}

If you need to specify a custom kubeconfig location:

{
  "mcpServers": {
    "openshift-python-wrapper": {
      "command": "openshift-mcp-server",
      "env": {
        "KUBECONFIG": "/home/user/.kube/config"
      }
    }
  }
}

# Check pod status
pod = get_resource("pod", "failing-app", "production")

# Get recent events
events = get_resource_events("pod", "failing-app", "production")

# Check logs
logs = get_pod_logs("failing-app", "production", tail_lines=200)

# Execute diagnostic command
exec_in_pod("failing-app", "production", ["cat", "/etc/app/config.yaml"])

# Apply all resources at once
yaml = """
---
apiVersion: v1
kind: Namespace
metadata:
  name: my-app
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: backend
  namespace: my-app
spec:
  replicas: 3
  selector:
    matchLabels:
      app: backend
  template:
    metadata:
      labels:
        app: backend
    spec:
      containers:
      - name: api
        image: myapp/backend:v1.0
        ports:
        - containerPort: 8080
---
apiVersion: v1
kind: Service
metadata:
  name: backend
  namespace: my-app
spec:
  selector:
    app: backend
  ports:
  - port: 80
    targetPort: 8080
"""
apply_yaml(yaml)

# List nodes
nodes = list_resources("node")

# Check for pod issues
problem_pods = list_resources("pod", field_selector="status.phase!=Running,status.phase!=Succeeded")

# Review recent events
events = list_resources("event", limit=50)

# Check CNV version
csv = list_resources("clusterserviceversion", namespace="openshift-cnv")

# List VMs
vms = list_resources("virtualmachine", namespace="my-vms")

# Check VM status
vm = get_resource("virtualmachine", "rhel9-vm", "my-vms")

The server dynamically discovers all available resource types from your cluster. Common types include:

• pod, service, deployment, replicaset, daemonset
• configmap, secret, persistentvolume, persistentvolumeclaim
• namespace, node, event, endpoint
• serviceaccount, role, rolebinding, clusterrole, clusterrolebinding

• route, project, imagestream, buildconfig, deploymentconfig
• user, group, oauth, securitycontextconstraints

• virtualmachine, virtualmachineinstance, datavolume
• hyperconverged, kubevirt, cdi

• clusterserviceversion, subscription, installplan, operatorgroup
• catalogsource, packagemanifest

1. RBAC: Ensure your kubeconfig has appropriate permissions
2. Namespaces: Use namespace isolation for multi-tenant environments
3. Resource Limits: Set appropriate limits when listing resources
4. Sensitive Data: Be careful with secrets and configmaps

# Test cluster connectivity
kubectl cluster-info

# Check kubeconfig
echo $KUBECONFIG
kubectl config current-context

# Check your permissions
kubectl auth can-i --list

# Run in debug mode
SIMPLE_LOGGER_LEVEL=DEBUG python mcp_server/server.py

# Check logs
tail -f /tmp/mcp_server_debug.log

1. Fork the repository
2. Create a feature branch
3. Add tests for new functionality
4. Submit a pull request

New resource types are automatically discovered from the cluster. To ensure proper support:

1. Add the resource module to ocp_resources/
2. Ensure it has api_group and api_version attributes
3. Test with the MCP server

This project is licensed under the Apache License 2.0.