Inspect Kubernetes and OpenShift resources with the containers project’s MCP server. Compare cluster contexts, workload tools and read-only configuration.
The containers project’s Kubernetes MCP server connects assistants to Kubernetes and OpenShift operations. It can provide cluster and workload context without treating container packaging as the integration’s purpose. The project documents configuration, toolsets and dedicated guidance for a read-only Kubernetes setup.
Start with the cluster context, namespace and workload name. Retrieve its state and relevant diagnostic information before forming an explanation. Keep the observed resource identifiers with the result so a deployment in another namespace is not mistaken for the target.
The README provides npx -y kubernetes-mcp-server@latest as a local launch. It also describes other distribution methods and configuration through a TOML file. Select the intended kubeconfig and review the read-only setting and toolsets. Actual cluster access is limited by the Kubernetes identity used for the connection.
Maintainer’s setup and tool reference. Browse kubernetes MCP servers for related workflows.
{
"mcpServers": {
"kubernetes": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
]
}
}
}Select the intended kubeconfig and review read_only and toolsets in the project configuration guide.
Access to a Kubernetes or OpenShift cluster through the configured identity and kubeconfig.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.
Container operations in conversation — inspect, run, debug and clean up Docker workloads.
Manage Docker containers and compose stacks through natural language with Claude AI.
Enables interaction with Kubernetes clusters through Model Control Protocol (MCP) tools.
Enables Claude Desktop to utilize Deepseek models running in Docker containers.
Provides natural language processing and API access to Kubernetes clusters, combining kubectl commands and the Kubernetes Python client.