Keep Roo Code.
Give it your machines.

AI Commander is not an alternative to Roo Code, Cline, Cursor, Claude Code, Codex, ChatGPT, Gemini, Grok, Windsurf, or Continue. 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.

Quick start:
  1. Install the host agent on the machine you want your AI to control. It shows a private machine code.
  2. Connect your AI: paste this prompt, then replace AIC-… with your code — Help me connect this AI client to AI Commander using https://aicommander.dev/start.md. Then check the status of my machine: AIC-… — or add the connector URL https://aicommander.dev/mcp and sign in with an email code (per-client steps).
Positioning in one line: Roo Code stays the brain; AI Commander is the hands on the box — servers, GPU rigs, NAS, laptops — with no inbound ports and no exposed SSH.

Sibling harness pages: Cursor · Aider · Cline · Roo Code · Zed · OpenCode · Qwen Code · Continue · Windsurf · Claude Code · Grok · Codex · ChatGPT · Gemini.

Connect Roo Code (MCP settings)

Roo Code is the VS Code AI agent extension (fork lineage of Cline, with its own MCP settings). It talks to AI Commander through the same stdio MCP bridge as Cursor, Cline, and Windsurf. Add this under mcpServers in Roo’s MCP settings (open Roo Code → gear → MCP Servers, then Edit Global MCP / Edit Project MCP, or edit mcp_settings.json / project .roo/mcp.json):

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

The config shape matches Cursor and other IDE MCP clients; only the settings path differs. Full client matrix (Roo Code, Cline, Cursor, Continue, Windsurf, Claude Code, Codex, ChatGPT, Gemini, Grok, REST): Connect your AI client.

Without AICOMMANDER_TOKEN in its env, the bridge connects anonymously with a code-only first hour. Set it to your API key to bind the bridge to your account.

What you get that the chat alone cannot

Not a replacement — a multiplier

You already useAI Commander adds
Roo CodeRoo MCP settings / mcp_settings.json / .roo/mcp.json + npx @aicommander/mcp
ClineCline MCP settings / cline_mcp_settings.json + npx @aicommander/mcp
Continue~/.continue/config.yaml / .continue/mcpServers/ + stdio bridge
Cursornpx @aicommander/mcp stdio bridge → remote exec + jobs
Windsurf (Devin Desktop)~/.config/devin/mcp_config.json + stdio bridge
Claude CodeMCP remote exec + jobs on your fleet
Codex / ChatGPTSame MCP endpoint or REST /api/v1/exec
Gemini / Grokgemini mcp add / grok mcp add --transport http …

How Roo Code handles MCP servers

Checked against Roo Code docs: Using MCP in Roo Code in November 2026. Client behaviour changes between releases; the official docs win if they disagree.

A workflow that suits Roo Code

Roo is good at long, multi-step tasks inside one repo. A pattern that works: keep the code in your editor and let Roo drive a separate build or test box.

  1. Add aicommander to your global mcp_settings.json as a "streamable-http" entry for https://aicommander.dev/mcp, with your own Authorization: Bearer <API key> header. Keep keys out of any committed .roo/mcp.json.
  2. Put the read-only tools in alwaysAllow: list_machines, session_status, remote_job_status and remote_job_logs. Leave remote_exec and remote_job_start on manual approval.
  3. Ask Roo to start the full test suite on the build box with remote_job_start, keep refactoring locally, then have it read remote_job_logs and fix whatever failed.

Limits and gotchas in Roo Code

FAQ

Is AI Commander an alternative to Roo Code?
No. AI Commander is a remote-machine harness. You keep Roo Code (or Cursor, Claude Code, Codex, ChatGPT, Gemini, Grok, Windsurf, Continue, Cline) as the AI. AI Commander gives those tools secure remote shell, detached jobs, and file transfer on machines you own — over MCP or REST.
How do I connect Roo Code to AI Commander?
Add the stdio bridge in Roo Code’s MCP settings (VS Code: open Roo Code → gear → MCP Servers → Edit Global MCP / Edit Project MCP, or edit mcp_settings.json / .roo/mcp.json) with npx -y @aicommander/mcp and AICOMMANDER_SERVER=https://aicommander.dev. Without AICOMMANDER_TOKEN in env the bridge connects anonymously, code-only; set it to your API key to bind it to your account. See /howto/ for the full matrix.
How is this different from Roo Code running locally only?
Local Roo Code is the brain in your editor. AI Commander adds hands on servers, GPU rigs, NAS, and other laptops you own — outbound-only, no inbound ports, no exposed SSH — so Roo can run shell, detached jobs, and file transfer on those machines over MCP.
Why does Roo report that the aicommander server timed out?
Roo's per-server timeout defaults to 60 seconds. A long command sent through remote_exec runs past it. Raise timeout for the server (up to 3600 seconds), or ask Roo to use remote_job_start and poll remote_job_status.
Can my whole team share one AI Commander setup in Roo?
Only partly. A .roo/mcp.json at the repo root overrides a global entry with the same name, and it is usually committed, so it must not hold a key. Let each person add the server to their own global settings with their own API key. The npx stdio bridge runs anonymously (code-only) unless AICOMMANDER_TOKEN is set.

Next steps

Install the agent on a machine you control, connect Roo Code via MCP settings, then ask for a real task on a remote box.