mcpField
K
Kubernetes MCP Server

Kubernetes MCP Server

Local
github.com/ehiaigCloud & Infra0Updated 82w ago
Repository

About Kubernetes MCP Server

Kubernetes MCP Server helps operators inspect Kubernetes YAML files and folders and manage connected clusters. It supports configuration analysis and basic pod operations; several other management features are marked as unimplemented.

Key features

  1. 01Analyze Kubernetes YAML files
  2. 02Analyze folders of YAML files
  3. 03List and inspect pods
  4. 04View pod logs and delete pods
  5. 05Connect to and manage clusters

Use cases

  1. 01Find issues in a Kubernetes YAML file
  2. 02Review configuration across a folder
  3. 03Inspect pod status and logs
  4. 04Remove a pod from a cluster

MCP support

It exposes Kubernetes configuration analysis and cluster operations to MCP clients, including pod listing, inspection, logs, and deletion.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Kubernetes MCP Server

An MCP server for debugging and managing Kubernetes config using Natural Language

This MCP Server lets you:

  1. Debug a kubernetes config yaml/yml file
  2. Debug an entire kubernetes config folder that contains yaml/yml files
  3. Connect and manage Kubernetes clusters

Features

  • Debug and analyze a kubernetes config yaml/yml file
  • Debug an entire kubernetes config folder that contains yaml/yml files
  • Pod management (list, get, logs, delete)
  • Deployment management (create, list, get, logs, delete)
  • Service management (Create, list, get, logs, delete)
  • Namespaces management (list, get, logs, delete)
  • Debug and Analyze Logs, Services, Seployment, Statefulset, Demonsets, Ingress, Node, Cluster
  • Portforward to a pod or service
  • Helm Chart installation and management

Quickstart

  1. Install Claude Desktop

  2. Install this MCP server

  • Using uv: uv

Run: uv pip install git+https://github.com/ehiaig/kubernetes-mcp-server

Or

  • Clone this repo: git clone https://github.com/ehiaig/kubernetes-mcp-server.git
  1. Open the Claude json file

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

And then add the following to your MCP servers file:

For Local testing with Claude Desktop

{
    "kubernetes-mcp-server": {
    "command": "/path/to/your/.local/bin/uv", // or "uv"
    "args": [
        "--directory",
        "/path/to/this/repo/kubernetes-mcp-server/src/k8s_manager",
        "run",
        "-m",
        "k8s_manager"
    ]
  }
}

Your claude_desktop_config.json file should look similar to this:

{
    "mcpServers": {
        "kubernetes-mcp-server": {
            "command": "/path/to/your/.local/bin/uv",
            "args": [
                "--directory",
                "/path/to/this/repo/kubernetes-mcp-server/src/k8s_manager",
                "run",
                "-m",
                "k8s_manager"
            ]
        }
    }
}

For Published Servers

"mcpServers": {
  "kubernetes-mcp-server": {
    "command": "uvx",
    "args": [
      "k8s_manager"
    ]
  }
}

🚧 Disclaimers

Sensitive Data

DO NOT CONFIGURE CLUSTERS WITH SENSITIVE DATA. This includes secrets, passwords, etc.

Any sensitive data exchanged with the LLM is inherently compromised, unless the LLM is running 100% on your local machine.

If you are interested in securely passing secrets to CLUSTERS, file an issue on this repository with your use-case.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.