Skip to main content
Glama
local-devops-mcp

local-devops-mcp

Local DevOps MCP Server

A Model Context Protocol (MCP) server that provides tools for local DevOps tasks, enabling AI assistants to interact with your local Docker environment, Kubernetes clusters, and system logs.

NOTE

This server usesTOON (Token-Oriented Object Notation) for tool outputs to optimize token usage for LLMs.

Features

🐳 Docker

Interact with your local Docker daemon:

  • docker_list_containers: List running or all containers.

  • docker_logs: Fetch logs from a container (with error highlighting 🔴).

  • docker_restart: Restart a specific container.

  • docker_inspect: Inspect container details.

☸️ Kubernetes

Interact with your local Kubernetes cluster (uses ~/.kube/config):

  • k8s_list_pods: List pods in a namespace.

  • k8s_pod_logs: Get logs from a pod.

  • k8s_describe_pod: Get detailed pod information.

🖥️ System

Access local system information:

  • system_open_ports: List open listening ports (requires lsof).

  • system_logs: Read system logs (e.g., /var/log/system.log).

Related MCP server: Docker MCP Server

Installation & Usage

Using npx (Recommended)

You can run the server directly without installation:

npx local-devops-mcp

Configuration for Claude Desktop

To use this server with Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "local-devops": {
      "command": "npx",
      "args": ["-y", "local-devops-mcp"]
    }
  }
}

Running from Source

  1. Clone the repository:

    git clone https://github.com/nguyentrantung205/local-devops-mcp.git
    cd local-devops-mcp
  2. Install dependencies:

    npm install
  3. Build the project:

    npm run build
  4. Run the server:

    node build/index.js

Prerequisites

  • Node.js: v18 or higher.

  • Docker: Docker Desktop or Docker Engine must be running locally.

  • Kubernetes: kubectl configured with a valid ~/.kube/config (optional, only for K8s tools).

  • Permissions: The user running the server needs permissions to access the Docker socket and read system logs.

Testing

See TESTING.md for instructions on how to test the server locally.

License

ISC

Available Tools

4 tools
docker_inspectD

Inputs: containerId (required).

docker_logsD

Inputs: containerId (required), tail.

k8s_list_podsD

Inputs: namespace.

k8s_pod_logsD

Inputs: name (required), container, namespace.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    D1.8/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a distinct prefix (docker or k8s) and action (logs, inspect, list_pods, pod_logs), making them clearly distinguishable even without descriptions.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case (e.g., docker_logs, k8s_list_pods), and the prefix consistently indicates the subsystem.

    Tool Count3/5

    With only 4 tools for a broad domain like local devops, the set feels too sparse to cover common operations, though each tool is distinct.

    Completeness2/5

    Obvious gaps: Docker only has logs and inspect (no run, stop, etc.) and Kubernetes only has list pods and pod logs (no get, delete, etc.), leaving agents unable to complete basic workflows.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to manage Docker containers, images, networks, volumes, and Compose services through the Model Context Protocol. It supports system operations, command execution within containers, and integration with Docker Hub and GitHub Container Registry.
      167 npm
      2
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      An AI-powered development assistant that enables LLMs to securely interact with local development tools including Git, filesystem, Docker, PostgreSQL, and GitHub via the Model Context Protocol.
      -
    • F
      license
      Not graded
      quality
      C
      maintenance
      Connects an AI assistant to local Docker and Kubernetes environments, enabling real-time command execution and log inspection with user approval.
      -