Keep OpenCode.
Give it your machines.
AI Commander is not an alternative to OpenCode, Claude Code, Codex, ChatGPT, Cursor, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, or Zed. 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.
- Install the host agent on the machine you want your AI to control. It shows a private machine code.
- 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 URLhttps://aicommander.dev/mcpand sign in with an email code (per-client steps).
Sibling harness pages: Cursor · Aider · Cline · Roo Code · Zed · OpenCode · Qwen Code · Continue · Windsurf · Claude Code · Grok · Codex · ChatGPT · Gemini.
Connect OpenCode (MCP CLI)
OpenCode is an open-source coding agent CLI with native remote HTTP MCP support. Point it at AI Commander’s hosted MCP endpoint:
Full client matrix (OpenCode, Claude Code, Codex, ChatGPT, Cursor, Grok, Gemini, Continue, Windsurf, Cline, Roo Code, Zed, REST): Connect your AI client.
First connect may open a one-time browser sign-in (OAuth Dynamic Client Registration).
For a code-only first hour without that flow, append ?anonymous=1 to the MCP URL.
For account features (saved aliases) with an API key instead of the sign-in, use the opencode.json variant below.
Or configure it in opencode.json
Per the OpenCode MCP docs (checked 2026-10-24), a remote server is an entry under mcp with type set to "remote" and a url.
Put this in opencode.json. OpenCode starts the OAuth sign-in the first time you use the server; if it does not, run opencode mcp auth aicommander.
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"aicommander": {
"type": "remote",
"url": "https://aicommander.dev/mcp"
}
}
}
To use an AI Commander API key from the dashboard instead, turn OAuth off and send the key as a Bearer header, the way the OpenCode docs show for API-key servers.
{env:AIC_API_KEY} reads the key from your environment, so it stays out of the file:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"aicommander": {
"type": "remote",
"url": "https://aicommander.dev/mcp",
"oauth": false,
"headers": {
"Authorization": "Bearer {env:AIC_API_KEY}"
}
}
}
}
API keys only act while you have opened the AI Commander dashboard within your access window (72 hours by default); for unattended runs (CI, cron) see Credential security on Connect your AI client.
OpenCode’s v2 preview docs nest servers under mcp.servers instead, so match the shape to your OpenCode version.
To check the connection, run opencode mcp list.
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, training, and headless agents on the box that has the repo.
- Fleet list + GPU facts so OpenCode picks the right machine before it burns an hour.
- File courier (Pro) for checkpoints and diffs up to 100 MiB.
Not a replacement — a multiplier
| You already use | AI Commander adds |
|---|---|
| OpenCode | opencode mcp add aicommander --url https://aicommander.dev/mcp |
| Claude Code | claude mcp add --transport http … → remote exec + jobs |
| Codex / ChatGPT | Same MCP endpoint or REST /api/v1/exec |
| Cursor | npx @aicommander/mcp stdio bridge → remote exec + jobs |
| Grok / Gemini | grok mcp add --transport http … / gemini mcp add |
| Cline / Roo Code / Zed | MCP settings / context_servers + bridge or remote URL |
| Continue / Windsurf | stdio bridge in Continue / Windsurf MCP config |
FAQ
Next steps
Install the agent on a machine you control, connect OpenCode via opencode mcp add, then ask for a real task on a remote box.