Awesome Linux MCP Server

A comprehensive Model Context Protocol (MCP) server that provides AI models with secure control over remote Linux servers and browser automation capabilities.

Features

SSH-Based Linux Server Control

• Remote Command Execution: Run commands securely on remote Linux servers via SSH
• Script Management: Execute and create bash scripts on remote systems
• File System Operations: List directories with detailed information
• System Monitoring: Comprehensive CPU, memory, and disk usage monitoring

Browser Automation

• Web Navigation: Navigate to URLs with automatic wait conditions
• Interactive Controls: Click, hover, fill forms, and select dropdown options
• Screenshot Capture: Full page or element-specific screenshots
• JavaScript Execution: Run custom JavaScript in browser context
• Real-time Monitoring: Console logs and network request tracking

MCP Resources

• Console Logs: Access browser console output as MCP resources
• Screenshots: Current browser screenshots as base64 data
• Network Details: HTTP request/response monitoring data

Installation

Prerequisites

• Python 3.8+
• SSH access to a Linux server
• Chrome/Chromium browser (for browser automation)

Setup

1. Clone or create the project directory:

   mkdir awesome-linux-mcp
   cd awesome-linux-mcp
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Configure environment variables:

   cp config.example.env .env
   # Edit .env with your SSH and configuration settings
   

4. Set up SSH access:

   • Ensure you have SSH access to your target Linux server
   • Use either SSH key authentication (recommended) or password authentication
   • Test SSH connection manually first: ssh user@host

Configuration

Environment Variables

*Either SSH_KEY_PATH or SSH_PASSWORD must be provided for authentication.

SSH Key Setup (Recommended)

1. Generate SSH key pair (if you don't have one):

   ssh-keygen -t ed25519 -C "your-email@example.com"
   

2. Copy public key to remote server:

   ssh-copy-id user@remote-server
   

3. Set SSH_KEY_PATH to the path of your private key (e.g., ~/.ssh/id_ed25519)

Running the Server

Development Mode

python linux_mcp_server.py

Testing the Server

You can test the MCP protocol directly:

echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | python linux_mcp_server.py

Claude Desktop Integration

Add the server to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "linux-server": {
      "command": "python",
      "args": ["/path/to/linux_mcp_server.py"],
      "env": {
        "SSH_HOST": "your-server.com",
        "SSH_USER": "your-username",
        "SSH_KEY_PATH": "/path/to/your/key",
        "BROWSER_HEADLESS": "true"
      }
    }
  }
}

Available Tools

Command Execution Tools

execute_command

Execute a single terminal command on the remote Linux server.

await execute_command("ls -la /home")

execute_script

Execute a bash script with optional arguments.

await execute_script("/path/to/script.sh", "--verbose")

create_bash_script

Create and deploy a new bash script to the remote server.

await create_bash_script("hello.sh", "echo 'Hello World'")

File System Tools

list_directory

List directory contents with detailed information.

await list_directory("/var/log")

System Monitoring Tools

get_system_info

Get comprehensive system information (CPU, memory, disk usage).

await get_system_info()

Browser Automation Tools

puppeteer_navigate

Navigate browser to a URL.

await puppeteer_navigate("https://example.com")

puppeteer_screenshot

Capture screenshot of page or element.

await puppeteer_screenshot("homepage", "", "1200", "800")

puppeteer_click

Click on a web page element.

await puppeteer_click("#submit-button")

puppeteer_hover

Hover over a web page element.

await puppeteer_hover(".menu-item")

puppeteer_fill

Fill a form input field.

await puppeteer_fill("#username", "myusername")

puppeteer_select

Select an option from a dropdown.

await puppeteer_select("#country", "US")

puppeteer_evaluate

Execute JavaScript in browser context.

await puppeteer_evaluate("document.title")

puppeteer_get_console_logs

Get browser console logs.

await puppeteer_get_console_logs()

puppeteer_get_screenshot

Get current browser screenshot.

await puppeteer_get_screenshot()

puppeteer_get_network_details

Get network request details.

await puppeteer_get_network_details()

MCP Resources

console://logs

Access browser console output.

# Access via MCP resource API

screenshot://current

Get current browser screenshot as base64.

# Access via MCP resource API

network://details

Get network request/response data as JSON.

# Access via MCP resource API

Security Considerations

SSH Security

• Use SSH…