Keep Trae.
Give it your machines.

AI Commander is not an alternative to Trae, Claude Code, Codex, ChatGPT, Cursor, GitHub Copilot, Sourcegraph Cody, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, Zed, OpenCode, Qwen Code, goose, Amp, Kilo Code, OpenHands, Amazon Q Developer, Augment Code, Devin, JetBrains Junie, Kiro, Warp, Factory, Crush, or LM Studio. It is the remote-machine harness those tools plug into over MCP: outbound-only shell, detached jobs that outlive the chat, and file transfer on hardware you already own.

Sibling harness pages: Claude Code · Codex · ChatGPT · Cursor · OpenCode · Factory · Kiro · Warp · Crush · LM Studio · Gemini — and the rest on Connect your AI client.

Connect Trae (remote MCP)

Trae, the AI IDE (Trae MCP docs), supports stdio servers and remote HTTP servers declared with a url (plus optional headers). Click the Settings icon (upper-right in IDE mode, or in the chat panel in SOLO mode), select MCP, then Add → Add Manually, and paste:

{
  "mcpServers": {
    "aicommander": {
      "url": "https://aicommander.dev/mcp"
    }
  }
}

Click Confirm and AI Commander appears in the MCP server list. Already have AI Commander in another IDE’s mcp.json? Use Raw Config (JSON) and paste the same entry. For a project-scoped server, add .trae/mcp.json in the repo root and enable project-level MCP under Settings → MCP — but that file is shared with your team, so never put an Authorization header or API key in it.

Prefer a local stdio bridge?

{
  "mcpServers": {
    "aicommander": {
      "command": "npx",
      "args": [
        "-y",
        "@aicommander/mcp"
      ],
      "env": {
        "AICOMMANDER_SERVER": "https://aicommander.dev"
      }
    }
  }
}

Trae’s stdio servers need npx on your PATH. Keep tool-call confirmations on for AI Commander at first; long builds and training runs are good candidates for detached jobs.

Full client matrix (Trae, Crush, LM Studio, Factory, Kiro, Warp, Junie, Claude Code, Codex, ChatGPT, Cursor, Copilot, Gemini, OpenCode, goose, and more, plus REST): Connect your AI client.

The first remote connection may open a one-time browser sign-in; for a code-only first hour, append ?anonymous=1 to the MCP URL. For optional account features (saved aliases), pass a Bearer API key in headers. Menus and options can differ between Trae versions — check the linked Trae docs for your build.

What you get that the chat alone cannot

• Remote shell on Linux, macOS, and Windows — by session code or saved alias.
• Detached jobs for builds, test suites, and training on the box that has the repo.
• Fleet list + GPU facts so Trae picks the right machine before it burns an hour.
• File courier (Pro) for checkpoints and diffs up to 100 MiB.
• Outbound-only agent on each machine — no inbound ports, no exposed SSH, no VPN to set up.

Not a replacement — a multiplier

FAQ