mcp-server-kubernetes

MCP Server that can connect to a Kubernetes cluster and manage it. Supports loading kubeconfig from multiple sources in priority order.

Before using this MCP server with any tool, make sure you have:

1. kubectl installed and in your PATH
2. A valid kubeconfig file with contexts configured
3. Access to a Kubernetes cluster configured for kubectl (e.g. minikube, Rancher Desktop, GKE, etc.)
4. Helm v3 installed and in your PATH (no Tiller required). Optional if you don't plan to use Helm.

You can verify your connection by running kubectl get pods in a terminal to ensure you can connect to your cluster without credential issues.

By default, the server loads kubeconfig from ~/.kube/config. For additional authentication options (environment variables, custom paths, etc.), see ADVANCED_README.md.

Add the MCP server to Claude Code using the built-in command:

claude mcp add kubernetes -- npx mcp-server-kubernetes

This will automatically configure the server in your Claude Code MCP settings.

Add the MCP server to Codex CLI using the built-in command:

codex mcp add kubernetes -- npx mcp-server-kubernetes

This registers the server globally in ~/.codex/config.toml and makes its tools available in all Codex sessions.

Add the following configuration to your Claude Desktop config file:

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"]
    }
  }
}

MCP Server Kubernetes is also available as a mcpb (formerly dxt) extension. In Claude Desktop, go to Settings (Cmd+, on Mac) -> Extensions -> Browse Extensions and scroll to find mcp-server-kubernetes in the modal. Install it & it will install & utilize kubectl via command line & your kubeconfig.

To manually install, you can also get the .mcpb by going to the latest Release and downloading it.

VS Code has built-in MCP support. Use the one-click install button above, or add the server to .vscode/mcp.json in your workspace (or to your user mcp.json via MCP: Open User Configuration):

{
  "servers": {
    "kubernetes": {
      "type": "stdio",
      "command": "npx",
      "args": ["mcp-server-kubernetes"]
    }
  }
}

Cursor supports MCP servers through its AI integration. Add the server to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"]
    }
  }
}

The server will automatically connect to your current kubectl context. You can verify the connection by asking the AI assistant to list your pods or create a test deployment.

Muse Code reads MCP servers from the mcp_servers block of ~/.config/muse/settings.json. The file must include "schema_version": 1:

{
  "schema_version": 1,
  "mcp_servers": {
    "kubernetes": {
      "transport": "stdio",
      "command": "npx",
      "args": ["mcp-server-kubernetes"]
    }
  }
}

To connect over Streamable HTTP instead, first start the server in HTTP mode (it serves /mcp on port 3000 by default; see Streamable HTTP Transport):

ENABLE_UNSAFE_STREAMABLE_HTTP_TRANSPORT=1 npx mcp-server-kubernetes

Then point Muse Code at that endpoint with the streamable_http transport (headers is optional):

{
  "schema_version": 1,
  "mcp_servers": {
    "kubernetes": {
      "transport": "streamable_http",
      "url": "http://localhost:3000/mcp",
      "mode": "optional"
    }
  }
}

"mode": "optional" lets Muse Code start with a warning if the HTTP server isn't running, instead of aborting.

Start a new Muse Code session after editing the file, then run /mcp to confirm the kubernetes server and its tools are connected.

mcp-chat is a CLI chat client for MCP servers. You can use it to interact with the Kubernetes server.

npx mcp-chat --server "npx mcp-server-kubernetes"

Alternatively, pass it your existing Claude Desktop configuration file from above (Linux should pass the correct path to config):

Mac:

npx mcp-chat --config "~/Library/Application Support/Claude/claude_desktop_config.json"

Windows:

npx mcp-chat --config "%APPDATA%\Claude\claude_desktop_config.json"

• Connect to a Kubernetes cluster
• Unified kubectl API for managing resources
  • Get or list resources with kubectl_get
  • Describe resources with kubectl_describe
  • List resources with kubectl_get
  • Create resources with kubectl_create
  • Apply YAML manifests with kubectl_apply
  • Delete resources with kubectl_delete
  • Get logs with kubectl_logs
  • Manage kubectl contexts with kubectl_context
  • Explain Kubernetes resources with explain_resource
  • List API resources with list_api_resources
  • Scale resources with kubectl_scale
  • Update field(s) of a resource with kubectl_patch
  • Manage deployment rollouts with kubectl_rollout
  • Execute any kubectl command with kubectl_generic
  • Verify connection with ping
• Advanced operations
  • Scale deployments with kubectl_scale (replaces legacy scale_deployment)
  • Port forward to pods and services with port_forward
  • Run Helm operations
    • Install, upgrade, and uninstall charts
    • Support for custom values, repositories, and versions
    • Template-based installation (helm_template_apply) to bypass authentication issues
    • Template-based uninstallation (helm_template_uninstall) to bypass authentication issues
  • Pod cleanup operations
    • Clean up problematic pods (cleanup_pods) in states: Evicted, ContainerStatusUnknown, Completed, Error, ImagePullBackOff, CrashLoopBackOff
  • Node management operations
    • Cordoning, draining, and uncordoning nodes (node_management) for maintenance and scaling operations
• Troubleshooting Prompt (k8s-diagnose)
  • Guides through a systematic Kubernetes troubleshooting flow for pods based on a keyword and optional namespace.
• Non-destructive mode for read and create/update-only access to clusters
• Secrets masking for security (masks sensitive data in kubectl get secrets commands, does not affect logs)
• OpenTelemetry Observability (opt-in)
  • Distributed tracing for all tool calls
  • Export to Jaeger, Tempo, Grafana, or any OTLP backend
  • Configurable sampling strategies
  • Rich span attributes (tool name, duration, K8s context, errors)
  • See docs/OBSERVABILITY.md for details

The MCP Kubernetes server includes optional OpenTelemetry integration for comprehensive observability. This feature is disabled by default and can be enabled via environment variables or Helm configuration.

Enable observability with environment variables:

export ENABLE_TELEMETRY=true
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

npx mcp-server-kubernetes

• All tool calls: kubectl_get, kubectl_apply, kubectl_logs, etc.
• Execution duration: How long each operation takes
• Success/failure status: Automatic error tracking
• Kubernetes context: Namespace, context, resource type
• Rich metadata: Host, process, and custom attributes

Works with any OTLP-compatible backend:

• Jaeger (open source)
• Grafana Tempo (open source)
• Grafana Cloud (commercial)
• Datadog, New Relic, Honeycomb, Lightstep, AWS X-Ray

See docs/OBSERVABILITY.md for comprehensive documentation including:

• Configuration options
• Deployment examples (Kubernetes, Helm, Claude Code)
• Sampling strategies
• Production best practices
• Troubleshooting guide

# Start Jaeger
docker run -d --name jaeger \
  -e COLLECTOR_OTLP_ENABLED=true \
  -p 16686:16686 \
  -p 4317:4317 \
  jaegertracing/all-in-one:latest

# Enable telemetry
export ENABLE_TELEMETRY=true
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
export OTEL_TRACES_SAMPLER=always_on

# Run server
npx mcp-server-kubernetes

# View traces: http://localhost:16686

The MCP Kubernetes server includes specialized prompts to assist with common diagnostic operations.

This prompt provides a systematic troubleshooting flow for Kubernetes pods. It accepts a keyword to identify relevant pods and an optional namespace to narrow the search. The prompt's output will guide you through an autonomous troubleshooting flow, providing instructions for identifying issues, collecting evidence, and suggesting remediation steps.

Make sure that you have bun installed. Clone the repo & install dependencies:

git clone https://github.com/Flux159/mcp-server-kubernetes.git
cd mcp-server-kubernetes
bun install

1. Start the server in development mode (watches for file changes):

bun run dev

1. Run unit tests:

bun run test

1. Build the project:

bun run build

1. Local Testing with Inspector

npx @modelcontextprotocol/inspector node dist/index.js
# Follow further instructions on terminal for Inspector link

1. Local testing with Claude Desktop

{
  "mcpServers": {
    "mcp-server-kubernetes": {
      "command": "node",
      "args": ["/path/to/your/mcp-server-kubernetes/dist/index.js"]
    }
  }
}

1. Local testing with mcp-chat

bun run chat

See the CONTRIBUTING.md file for details.

You can run the server in a non-destructive mode that disables all destructive operations (delete pods, delete deployments, delete namespaces, etc.):

ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS=true npx mcp-server-kubernetes

For Claude Desktop configuration with non-destructive mode:

{
  "mcpServers": {
    "kubernetes-readonly": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"],
      "env": {
        "ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS": "true"
      }
    }
  }
}

All read-only and resource creation/update operations remain available:

• Resource Information: kubectl_get, kubectl_describe, kubectl_logs, explain_resource, list_api_resources
• Resource Creation/Modification: kubectl_apply, kubectl_create, kubectl_scale, kubectl_patch, kubectl_rollout
• Helm Operations: install_helm_chart, upgrade_helm_chart, helm_template_apply, helm_template_uninstall
• Connectivity: port_forward, stop_port_forward
• Context Management: kubectl_context

The following destructive operations are disabled:

• kubectl_delete: Deleting any Kubernetes resources
• uninstall_helm_chart: Uninstalling Helm charts
• cleanup: Cleanup of managed resources
• cleanup_pods: Cleaning up problematic pods
• node_management: Node management operations (can drain nodes)
• kubectl_generic: General kubectl command access (may include destructive operations)
• exec_in_pod: Arbitrary command execution inside a pod (can read service-account tokens and change state)

For additional advanced features, see the ADVANCED_README.md and also the docs folder for specific information on helm_install, helm_template_apply, node management & pod cleanup.

See this DeepWiki link for a more indepth architecture overview created by Devin.

This section describes the high-level architecture of the MCP Kubernetes server.

The sequence diagram below illustrates how requests flow through the system:

sequenceDiagram
    participant Client
    participant Transport as Transport Layer
    participant Server as MCP Server
    participant Filter as Tool Filter
    participant Handler as Request Handler
    participant K8sManager as KubernetesManager
    participant K8s as Kubernetes API

    Note over Transport: StdioTransport or<br>SSE Transport

    Client->>Transport: Send Request
    Transport->>Server: Forward Request

    alt Tools Request
        Server->>Filter: Filter available tools
        Note over Filter: Remove destructive tools<br>if in non-destructive mode
        Filter->>Handler: Route to tools handler

        alt kubectl operations
            Handler->>K8sManager: Execute kubectl operation
            K8sManager->>K8s: Make API call
        else Helm operations
            Handler->>K8sManager: Execute Helm operation
            K8sManager->>K8s: Make API call
        else Port Forward operations
            Handler->>K8sManager: Set up port forwarding
            K8sManager->>K8s: Make API call
        end

        K8s-->>K8sManager: Return result
        K8sManager-->>Handler: Process response
        Handler-->>Server: Return tool result
    else Resource Request
        Server->>Handler: Route to resource handler
        Handler->>K8sManager: Get resource data
        K8sManager->>K8s: Query API
        K8s-->>K8sManager: Return data
        K8sManager-->>Handler: Format response
        Handler-->>Server: Return resource data
    end

    Server-->>Transport: Send Response
    Transport-->>Client: Return Final Response

See this DeepWiki link for a more indepth architecture overview created by Devin.

Go to the releases page, click on "Draft New Release", click "Choose a tag" and create a new tag by typing out a new version number using "v{major}.{minor}.{patch}" semver format. Then, write a release title "Release v{major}.{minor}.{patch}" and description / changelog if necessary and click "Publish Release".

This will create a new tag which will trigger a new release build via the cd.yml workflow. Once successful, the new release will be published to npm. Note that there is no need to update the package.json version manually, as the workflow will automatically update the version number in the package.json file & push a commit to main.

Adding clusters to kubectx.

If you find this repo useful, please cite:

@software{Patel_MCP_Server_Kubernetes_2024,
author = {Patel, Paras and Sonwalkar, Suyog},
month = jul,
title = {{MCP Server Kubernetes}},
url = {https://github.com/Flux159/mcp-server-kubernetes},
version = {2.5.0},
year = {2024}
}