Glossary
The words used across the apps, the dashboard and these docs, in alphabetical order.
| Term | Meaning |
|---|---|
| Agent | The WECOMMANDER program on a machine that carries out tool calls. It connects out to the gateway and enforces the device's limits. |
| Allowed folders | The only folders an agent's file tools may touch (also called allowed roots). |
| Allowed commands (allowlist) | Command patterns that run without approval under standard trust; process_exec only. |
| API access key | A secret for MCP clients and scripts that use a bearer token; it acts with the role it was given. |
| Approval | A person's decision that one exact high-risk action may run once. |
| Audit log | The record of every tool call, approval and permission change. |
| Autonomous mode | Full trust for many devices for a time, with automatic expiry. |
| Classic mode | The Windows app without the Dock, working in windows. |
| Connector | The WECOMMANDER app on your computer when it carries AI calls to SSH servers (Hybrid Access). |
| Device | A machine with the agent, enrolled in a workspace. |
| Dock | The taskbar-like bar of the Windows app on a screen edge, with live server meters and panels. |
| Gateway | The WECOMMANDER service at wecommander.app: MCP endpoint, sign-in, approvals, audit and the dashboard. |
| Host / server | A saved connection in the desktop app (SSH, Telnet, serial or Mosh). |
| Hybrid Access | Sharing SSH servers with AI through your own computer, with nothing installed on the server. |
| Identity | A reusable user name with a key or password for many servers. |
| Known hosts | The servers' host keys you trusted. |
| Management Center | The part of the desktop app that handles sign-in, approvals, autonomous mode and the agent; on Linux, the app itself. |
| MCP | Model Context Protocol, the open standard AI assistants use to call tools. |
| Preset | How a shared SSH server may be used by AI: read only, with approval, or timed autonomous (local only). |
| Run as | Whether an agent's commands run as its normal user or as root. |
| Safety net | A list of catastrophic commands refused on every trust level. |
| Scheduled task | A command WECOMMANDER runs for you on a schedule. |
| Secret masking | Replacing passwords, tokens and keys in output with [REDACTED] before the AI sees it. |
| Snippet | A saved command you send into a terminal. |
| Target | A place AI tools can act on: an agent device or a shared SSH server (targets_list). |
| Team library | Servers and snippets shared with the workspace, end-to-end encrypted. |
| Trust level | strict, standard or full: how many high-risk actions need an approval on a device or SSH server. |
| Workspace | The account unit that owns devices, members, approvals, audit and the plan. |
- Documentation: The complete WECOMMANDER guide, A to Z: install, the desktop SSH client, server management, scheduled tasks, connecting Claude, ChatGPT, Cursor and VS Code over MCP, every MCP tool, AI permissions, approvals, security and troubleshooting.
- Frequently asked questions: Answers about connecting AI assistants to your computers and servers with WECOMMANDER: safety, supported systems, clients and local mode.