Keep Amazon Q Developer.
Give it your machines.
AI Commander is not an alternative to Amazon Q Developer, Claude Code, Codex, ChatGPT, Cursor, GitHub Copilot, Sourcegraph Cody, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, Zed, OpenCode, Qwen Code, goose, Amp, or Kilo Code. 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 · GitHub Copilot · Cody · OpenHands · Augment · Devin · Aider · Cline · Roo Code · Zed · OpenCode · Qwen Code · goose · Amp · Kilo Code · Continue · Windsurf · Claude Code · Grok · Codex · ChatGPT · Gemini.
Connect Amazon Q Developer (MCP HTTP)
Amazon Q Developer (MCP docs) supports remote MCP servers over HTTP in the CLI / Q Chat, and MCP in the IDE chat. Point it at AI Commander’s hosted MCP endpoint:
{
"mcpServers": {
"aicommander": {
"type": "http",
"url": "https://aicommander.dev/mcp"
}
}
}
CLI / Q Chat: add or edit the remote server in your Amazon Q agent configuration
(qchat mcp add for managed entries; remote HTTP uses type + url as above).
After connect, run /mcp in the CLI if OAuth is required and follow the browser URL.
IDE: Amazon Q Chat → Configure MCP servers → add an HTTP server named aicommander with
URL https://aicommander.dev/mcp (global ~/.aws/amazonq/ or workspace .amazonq/).
Prefer a local stdio bridge?
Wire that command under mcpServers.aicommander with command/args
(and optional env AICOMMANDER_SERVER=https://aicommander.dev) in
~/.aws/amazonq/mcp.json or your agent default.json — same pattern as other stdio MCP clients.
Full client matrix (Amazon Q, Claude Code, Codex, ChatGPT, Cursor, Copilot, Cody, Grok, Gemini, OpenCode, Qwen Code, goose, Amp, Kilo Code, Continue, Windsurf, Cline, Roo Code, Zed, REST): Connect your AI client. Amazon Q MCP docs: Using MCP with Amazon Q Developer · CLI MCP config · IDE MCP config.
Over the remote URL, first connect may open a one-time browser sign-in (OAuth Dynamic Client Registration).
The npx bridge does not sign in through a browser: without AICOMMANDER_TOKEN in its env it connects anonymously with a code-only first hour; set it to your API key to bind it to your account.
On the remote URL, append ?anonymous=1 to skip the sign-in, for a code-only first hour.
For optional account features (saved aliases), pass a Bearer API key header where your Amazon Q build supports it.
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 Amazon Q 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 |
|---|---|
| Amazon Q Developer | type: http → https://aicommander.dev/mcp (or npx -y @aicommander/mcp) |
| OpenHands | openhands mcp add aicommander --transport http https://aicommander.dev/mcp |
| Amp | amp mcp add aicommander https://aicommander.dev/mcp |
| goose | goose session --with-streamable-http-extension "https://aicommander.dev/mcp" |
| Kilo Code | mcp.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 / Continue / Windsurf | npx @aicommander/mcp stdio bridge |
| Copilot / Cody | HTTP MCP / cody.mcpServers + bridge |
| Cline / Roo Code / Zed | MCP settings / context_servers + bridge or remote URL |
How Amazon Q Developer handles MCP servers
- AWS has announced end of support for the Amazon Q Developer IDE plugins on April 30, 2027, and points users to Kiro.
- The CLI manages servers with
qchat mcp add,remove,list,importandstatus.--argstakes a comma-separated list (escape literal commas) or a JSON array. - Remote servers are written in the agent config as
"type": "http"with aurl. - For OAuth servers, Q lists the server as not yet loaded. Run
/mcpto get the sign-in URL and finish it in a browser.
Checked against AWS docs: MCP configuration for Amazon Q Developer CLI and AWS: Amazon Q Developer IDE plugins end of support in November 2026. Client behaviour changes between releases; the official docs win if they disagree.
A workflow that suits Amazon Q Developer
Many Q users already work in AWS all day. AI Commander covers what Q can't reach: machines outside AWS, such as an on-prem build server, a lab GPU box or a NAS.
- Add
aicommanderas an HTTP server in the Q CLI agent config and complete the/mcpsign-in. - Ask Q to compare a deployment: query the AWS side with its usual tools, then run
remote_execon the on-prem box to check the same service version and config. - For a long sync or build, have Q start it with
remote_job_startand checkremote_job_statusbefore you close the session.
Limits and gotchas in Amazon Q Developer
- If you use the IDE plugin, plan the move to Kiro before April 30, 2027. Kiro reads
mcpServersfrom.kiro/settings/mcp.json: copy theaicommanderentry over and check its fields against Kiro's MCP configuration page. - When passing
--argstoqchat mcp add, a value with a comma needs escaping, or use the JSON array form.
FAQ
npx bridge never does: it connects anonymously unless AICOMMANDER_TOKEN is set in its env. On the remote URL, use ?anonymous=1 for a code-only first hour. See /howto/ for the full matrix.aicommander entry into .kiro/settings/mcp.json or ~/.kiro/settings/mcp.json and check its fields against Kiro's MCP configuration page./mcp, open the URL it prints and sign in.aicommander entry and checking its fields against Kiro's format.--args as a JSON array. Without that, Q splits the value into two arguments.Next steps
Install the agent on a machine you control, connect Amazon Q Developer via remote HTTP MCP (or npx -y @aicommander/mcp), then ask for a real task on a remote box.