Short definition
The marketed Agent door is one command on this machine:
appaloft setup agentIt copies the Appaloft skill and writes token-free MCP into the hosts you already use. It does not deploy an app. Deploy stays appaloft up.
Workspace, Sandbox, and later preview surfaces are public alpha. They are not the start-page story.
flowchart TD
SETUP["appaloft setup agent\nskill + MCP on this machine"] --> SKILL["Full Appaloft Skill\ncapability entrypoint"]
SKILL --> DEPLOY["Agent Deploy Subprotocol\ncalls existing CLI/API/Web"]
SKILL --> LATER["Workspace / Sandbox\nlater, public alpha"]
DEPLOY --> OP["Shared business operations"]
LATER --> OP
Why this group exists
When an AI agent operates Appaloft, it must follow exactly the same boundaries as a human user: it can’t bypass the application layer to operate the database, SSH, or a provider SDK directly, can’t read plaintext secrets, and can’t invent “agent-exclusive operations” that only it can call. This group collects the rules for “how an agent should use Appaloft safely” in one place, instead of repeating them scattered across every feature page.
Start with appaloft setup agent. Read Workspace and Sandbox pages only when you need those later surfaces.
Core concepts at a glance
| Concept | One-line description | Detail |
|---|---|---|
| Appaloft Skill | The agent’s complete capability manual, mapped to the same operations as CLI/API/Web | Full Appaloft Skill |
| Deploy subprotocol | How an agent safely triggers a deployment | Agent Deploy Subprotocol |
| Agent Workspace | Later surface: long-lived collaboration on a Sandbox, currently public alpha | Agent Workspace |
| Sandbox | Later surface: isolated execution environment behind Workspace, currently public alpha | Sandbox Model |
| Task Run | Submitting, observing, and reviewing one agent execution on a Sandbox | Workspace Collaboration And Pause/Resume |
| Agent adapters | How to install and choose a specific agent runtime | Agent Adapters |
| Preview and promotion | Agent-driven preview deployment and production promotion flow | Agent Previews And Promotion |
| Delivery evidence | Verifiable evidence after a deployment completes | Delivery Evidence |
| MCP | The tool-calling protocol layer | MCP and tool protocols |
| Grok Bot plugin | Install skills/appaloft plus hosted MCP in Grok Bot | Grok Bot plugin |
Common mistakes
- Treating
appaloft setup agentas a deploy: it only teaches local hosts. Deploy withappaloft up. - Treating agent deployment as a new business operation: agent deployment only translates “deploy this project” into existing project, server, environment, and resource operations — it never adds capabilities only an agent can call.
- Letting an agent read
.env, private keys, or token files directly: an agent should always work through the CLI/API/Web/MCP entrypoints — secrets should be injected through a trusted secret manager or environment variables, never read directly by the agent. - Assuming Appaloft uploads artifacts to a managed cloud: unless the user explicitly opts into Appaloft Cloud’s managed capability, the default deployment target is still the BYOS server the user chose themselves.
- Starting on Workspace or Sandbox: those pages are later and public alpha, not the Agent door.
Related tasks
Advanced details
MCP (Model Context Protocol) is Appaloft’s protocol layer for tool-calling scenarios, sharing the same operation catalog as CLI/HTTP API/Web. Once MCP is configured, the Skill can use it as a callable tool layer; without it configured, the Skill still works normally through CLI/HTTP API/Web.