Skip to main content
Glama
ddjain
by ddjain

mcp-kubernetics

A Model Context Protocol (MCP) server that provides Kubernetes cluster introspection tools. It exposes various helper functions like listing pods, namespaces, node details, and more via MCP tools.

Features

  • List all pods in all namespaces

  • List pods by namespace

  • List all namespaces

  • Describe a specific pod

  • Get sorted events from a namespace

  • Get node resource usage (CPU, Memory)

  • Get node taints and labels

Related MCP server: Claude Ops Investigator

Installation

  1. Clone the repository:

    git clone <repository-url>
    cd mcp-kubernetics
  2. Install dependencies:

    npm install
  3. Build the project:

    npm run build

    This will generate a build folder containing index.js.

Usage

Running with Claude AI

  1. Open Claude desktop app.

  2. Go to Settings.

  3. Click on Developers.

  4. Click on Edit Config.

  5. This opens claude_desktop_config.json. Add the full path to the index.js file inside the args array as shown below.

  6. Save the file.

  7. Now you can ask questions related to your Kubernetes cluster like: "What are the pods in my cluster?"

Example claude_desktop_config.json snippet

Replace <FULL PATH OF BUILD> with the absolute path to your built index.js file.

{
  "mcpServers": {
    "kubernetics-mcp-server": {
      "command": "node",
      "args": ["<FULL PATH OF BUILD>/kubernetics-server/build/index.js"]
    }
  }
}

Available Tools

  • get-kubernetics-namespaces: Returns a list of namespaces in the cluster.

  • get-kubernetics-pods-detail-by-namespace: Returns pod details filtered by namespace.

  • get-kubernetics-all-pods-detail: Returns all pod details from the cluster.

  • describe-kubernetics-pod: Describe a specific pod by name and namespace.

  • get-kubernetics-events: Get sorted events from a namespace.

  • get-kubernetics-top-nodes: Get CPU and memory usage for nodes.

  • get-kubernetics-node-details: Get Kubernetes node taints and labels.

Contributing

Contributions are welcome! Please open issues or pull requests.

License

MIT License

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

  • Provides read access to your GKE and Kubernetes resources.

  • 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 costs—all without needing to parse text output or use complex kubectl commands.

  • Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.

  • The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.

Related MCP Servers

  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables read-only Kubernetes incident investigation through MCP tools for listing pods, describing resources, fetching logs, and searching runbooks.
    1
    -
  • A
    license
    A
    quality
    A
    maintenance
    Enables MCP clients to inspect and operate Kubernetes clusters across multiple contexts, with read-only/read-write/admin access modes and security flags controlling namespaces, contexts, deletes, applies, and exec.
    10
    512
    2
    MIT