VM Terminal

by leomercier

4 stars

Not rated

GitHub

About

Provides a secure web-based terminal interface for remote VM command execution through WebSocket connections and automatic tunnel creation, eliminating the need for direct SSH access.

Details

Author: leomercier
Repository: leomercier/mcp-tunnel
GitHub stars: 4
Categories: Design, Developer Tools, Frontend, Infrastructure
Tags: #web

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name VM Terminal

Command (node, npx, python, etc.) npm
Arguments
- Argument 1 start
Environment
- PORT 8080
- LOCALTUNNEL_SUBDOMAIN your-preferred-subdomain
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "/c",
                "npm",
                "start"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "/c",
                "npm",
                "start"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "/c",
                "npm",
                "start"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "/c",
                "npm",
                "start"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "/c",
                "npm",
                "start"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

From the repository

1. Start the MCP server:

bash npx mcp-cli

bash npm install -g mcp-cli mcp-cli


npm install

Create a .env file to configure the server:


PORT=8080
LOCALTUNNEL_SUBDOMAIN=your-preferred-subdomain

`execute_command`

Run a shell command on the VM. Parameters: { 'command': 'your shell command' }

`start_tunnel`

Create a web tunnel to access the VM interface. Parameters: { 'port': 8080, 'subdomain': 'optional-subdomain' }

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "vm terminal": {
            "env": {
                "PORT": "8080",
                "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
            },
            "args": [
                "start"
            ],
            "command": "npm"
        }
    }
}

Linux

{
    "env": {
        "PORT": "8080",
        "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
    },
    "args": [
        "start"
    ],
    "command": "npm"
}

Macos

{
    "env": {
        "PORT": "8080",
        "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
    },
    "args": [
        "start"
    ],
    "command": "npm"
}

Windows

{
    "env": {
        "PORT": "8080",
        "LOCALTUNNEL_SUBDOMAIN": "your-preferred-subdomain"
    },
    "args": [
        "/c",
        "npm",
        "start"
    ],
    "command": "cmd"
}

MCP Tunnel

A simple MCP (Model Context Protocol) server that allows accessing the command line of a VM machine. When started, it also tunnels the host to the web so it can be accessed via MCP.

Features

- Execute shell commands on a VM through MCP
- Web-based terminal interface for VM interaction
- Automatic tunneling to make the VM accessible from anywhere
- WebSocket-based real-time communication

Prerequisites

- Node.js (v18 or newer)

Installation and Usage

Running with npx (no installation)

npx mcp-cli

Global Installation

npm install -g mcp-cli
mcp-cli

Local Development

# Clone repository
git clone [repository-url]
cd mcp-cli
Install dependencies
npm install

Development

Run the development server with hot-reloading for both backend and frontend:

npm run dev

Building

Build both the frontend and backend for production:

npm run build-all

Usage

1. Start the MCP server:

# Start with automatic tunneling
npm start
Start without automatic tunneling
npm start -- --no-tunnel

This will build the project and start the server. By default, a tunnel will be created automatically. Use the --no-tunnel flag to disable automatic tunneling.

2. The server will start and provide output on stderr (to avoid interfering with MCP communication on stdout)

3. Use MCP to interact with the server using the following tools:

Available MCP Tools

- execute_command: Run a shell command on the VM
- Parameters: { "command": "your shell command" }
- start_tunnel: Create a web tunnel to access the VM interface
- Parameters: { "port": 8080, "subdomain": "optional-subdomain" }

Web Interface

After starting the tunnel, you can access the web-based terminal interface at the URL provided by the tunnel. This interface allows you to:

- Execute commands directly in the VM
- See command outputs in real-time
- Interact with the VM from any device with web access

Environment Variables

Create a .env file to configure the server:

# Server configuration
PORT=8080
Localtunnel configuration
LOCALTUNNEL_SUBDOMAIN=your-preferred-subdomain

Security Considerations

This tool provides direct access to your VM's command line. Consider these security practices:

- Use strong authentication mechanisms before exposing the tunnel
- Limit the commands that can be executed through proper validation
- Consider running in a restricted environment
- Do not expose sensitive information through the tunnel

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

execute_command

start_tunnel

Claude Desktop / Cursor

Linux

Macos

Windows

MCP Tunnel

Features

Prerequisites

Installation and Usage

Running with npx (no installation)

Global Installation

Local Development

Install dependencies

Development

Building

Usage

Start without automatic tunneling

Available MCP Tools

Web Interface

Environment Variables

Localtunnel configuration

Security Considerations

Install

More like this

Sentry

Github

Git

GitLab

Context 7

Playwright

`execute_command`

`start_tunnel`