What can Kubernetes MCP do?
It can list and describe pods, deployments, services, namespaces, configmaps, read logs, apply manifests, and manage resources.
Cloud & InfrastructureFreeactiveReviewed by MCPIndex
Kubernetes MCP Server
MCP server for complete Kubernetes and OpenShift cluster management via AI including pods, deployments, services, and logs.
Looking for more MCP servers? Browse the full MCP tools directory or explore more tools in Cloud & Infrastructure.
Reviewed by MCPIndex
MCPIndex assessment
Kubernetes MCP gives AI assistants read access to cluster state, enabling them to inspect pods, deployments, services, and namespaces during debugging sessions. For platform and DevOps teams that frequently deal with failed rollouts, CrashLoopBackOff errors, or resource limit issues, this reduces the back-and-forth between kubectl commands and the AI client. It is a practical tool for operational triage, not for cluster configuration or deployment management. Credential scoping to a specific namespace is strongly recommended before use.
Quick overview
Kubernetes MCP Server by Flux159 has 100K+ installs and provides full Kubernetes cluster management through AI assistants. It enables listing pods, deployments, services, and namespaces, reading logs, applying manifests, and managing OpenShift resources. It connects to any cluster through your existing kubeconfig file.
Best for
The teams and workflows that benefit most from this tool.
Platform and DevOps teams that need AI help during live Kubernetes cluster debugging.
Inspecting pod status, deployment health, and service configuration without running kubectl manually.
Faster incident triage when cluster state context is needed alongside AI analysis.
What this MCP server is best for
- Monitoring pods, deployments, services, and namespaces through Kubernetes MCP Server when you need quick visibility into a live Kubernetes cluster.
- Useful for debugging failed rollouts, CrashLoopBackOff errors, image pull failures, unhealthy services, and resource limit issues without jumping between kubectl commands.
- Best for platform and DevOps teams that want faster incident response, cluster inspection, and day-to-day operational troubleshooting from an AI assistant.
When to choose it
Choose Kubernetes MCP Server when you want an MCP server focused on Cloud & Infrastructure and need tighter integration with your existing tools.
Good fit
kubernetesk8sopenshiftdevopscloudinfrastructure
Limitations
Things to watch before choosing this tool.
Should be scoped to specific namespaces or read-only access to avoid unintended cluster changes.
Not a replacement for proper GitOps or deployment management practices.
Less useful for teams with simple single-service Kubernetes setups.
Kubernetes MCP Server Configuration
Use the following configuration as a starting point for Claude Desktop or any compatible MCP client, then replace placeholder credentials with your own values.
claude_desktop_config.json
{"mcpServers":{"kubernetes":{"command":"npx","args":["-y","mcp-server-kubernetes"]}}}How to set up Kubernetes MCP Server
These setup steps cover the typical installation flow for this MCP server.
- 1
Ensure kubectl is installed and configured with access to your cluster
- 2
Verify your kubeconfig is at the default path (~/.kube/config) or set KUBECONFIG
- 3
Add the Kubernetes MCP config to claude_desktop_config.json
- 4
Restart Claude Desktop
- 5
Ask Claude to list pods, check deployment status, or read logs from a service
Compatibility
Supported environments for Kubernetes MCP Server.
Claude Desktop
Yes
Cursor
No
VS Code
No
Operations-focused. Strongly recommended to use a read-only kubeconfig scoped to the relevant namespace.
Frequently asked questions
Common questions for Kubernetes MCP Server.
Does it support OpenShift?
Yes. It supports both standard Kubernetes and Red Hat OpenShift clusters.
Is my cluster access secure?
It uses your existing kubeconfig and local credentials. No credentials are sent externally.
Can it deploy applications?
Yes. Claude can apply YAML manifests and update deployments through the MCP server.
Does it work with cloud Kubernetes clusters?
Yes. It works with EKS, GKE, AKS, and any cluster accessible through your kubeconfig.