Kubernetes Ephemeral Job

Overview

Kubernetes Ephemeral Job is a Model Context Protocol server that executes commands in temporary Kubernetes pods and returns exit codes, output, and artifacts. Any MCP-compatible AI assistant can invoke its tools directly, letting the model decide when to run jobs as part of a conversation or agent workflow.

The server runs locally via Docker image docker.io/idconstruct/mcp-k8s-ephemeral-job:v0.7.1, communicating over stdio. You'll need to set the MCP_K8S_ALLOWED_IMAGES environment variable to configure which images are permitted. Version v0.7.1 is available under the MIT license, with source code at inhuman/mcp-k8s-ephemeral-job on GitHub.

This Cloud Service is compatible with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others in the broader ecosystem. If you maintain this project, claim your listing on mcp.site to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "kubernetes_ephemeral_job": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/idconstruct/mcp-k8s-ephemeral-job:v0.7.1"
      ],
      "env": {
        "MCP_K8S_ALLOWED_IMAGES": "<mcp-k8s-allowed-images>"
      }
    }
  }
}

Requires MCP_K8S_ALLOWED_IMAGES