Getting started
WECOMMANDER is three things that work together: a desktop SSH client with server management, an agent that connects your machines to your account, and one remote MCP URL that lets AI assistants such as Claude and ChatGPT work on those machines while you stay in charge. This page walks the whole path once; every step links to its detailed page.
What you need
- A computer with Windows 10 or 11 (x64), macOS 13 or newer, or a Linux server (Ubuntu or Debian, amd64) for the agent.
- For AI features: a WECOMMANDER account (free to create) and an AI client that supports remote MCP servers, such as Claude, ChatGPT, Cursor or VS Code.
- The SSH client in the Windows and macOS apps works without an account and without AI. An account adds sync, the team library, AI access, approvals and scheduled tasks.
1. Create your account
- Open https://wecommander.app/register and enter your e-mail address and a password of at least 12 characters.
- Open the verification link in the e-mail. Your account and its first workspace are created when you confirm.
- You land in the web dashboard. Every new workspace starts on the Free plan; see Plans and billing for limits and upgrades.
2. Install WECOMMANDER on your computer
On Windows and macOS you install one app; the agent comes inside it and connects this computer to your account after you sign in through the browser. On a Linux server you install the agent alone with one command.
# Windows (PowerShell)
irm https://wecommander.app/install.ps1 | iex
# macOS (Terminal) and Linux servers
curl -fsSL https://wecommander.app/install.sh | shEach installer downloads the package from the official release, checks its SHA-256 checksum and stops if it does not match. Details for every system, including the Microsoft Store copy and Windows servers without a desktop, are on Download and install.
3. Connect a server
There are two ways to bring a server under WECOMMANDER, and you can use both:
- With the agent: run the install command on the server and approve the device in your browser. The server keeps one outbound encrypted connection; no inbound port, VPN or SSH key is needed. It works while your own computer is off.
- Over SSH: add the server in the desktop app with its address and an SSH key or password. Nothing is installed on the server. You can later share it with AI through your own computer (Hybrid Access).
4. Connect your AI assistant
Add https://wecommander.app/mcp to your AI client as a remote MCP server and sign in with your WECOMMANDER account (OAuth). The AI then sees the devices and servers of your workspace through devices_list and targets_list.
5. Approve the first risky action
Reading files and checking a server's status run directly. Running a command, deleting a file, killing a process, opening a terminal or restarting a container waits for a person's approval of that exact action, unless you allowed it in the device's AI permissions. Approve it in the web dashboard (Approvals), from the e-mail link, or from the notification of the desktop app.
Next steps
- Download and install: Install the WECOMMANDER app on Windows (installer, PowerShell or Microsoft Store) and macOS, the agent on Linux and Windows servers, and the Management Center on Linux desktops.
- The web dashboard: A tour of the wecommander.app dashboard: overview, devices, terminal, files, tasks, scheduled tasks, approvals, MCP tools, team, audit log, usage and billing.
- AI access with MCP: how it works: What MCP (Model Context Protocol) is, the one WECOMMANDER MCP URL (https://wecommander.app/mcp), how a tool call reaches your machine, and the two ways to connect a server: the agent or SSH.
- AI permissions: trust levels, allowed commands, root and the safety net: Set per device and per SSH server what AI may do without asking: strict, standard or full trust (time-limited or not), allowed command patterns, run as root with two keys, the safety net and autonomous mode.
- Approvals: web, e-mail and desktop notifications: How a high-risk AI action waits for a person, where approval requests arrive (dashboard, e-mail, Windows and macOS notifications, Linux Management Center) and what one approval allows.
Set up WECOMMANDER and connect an AI assistant to your machine
- Create an account at https://wecommander.app/register and verify your e-mail address.
- Install WECOMMANDER: irm https://wecommander.app/install.ps1 | iex on Windows, or curl -fsSL https://wecommander.app/install.sh | sh on macOS and Linux servers.
- Sign in through the browser page that opens and approve the device; choose the folder the AI may use.
- Add https://wecommander.app/mcp to Claude, ChatGPT, Cursor or VS Code as a remote MCP server and sign in with OAuth.
- Ask the AI to work on the machine and approve risky actions in the dashboard, by e-mail or from the desktop notification.