Keep Sourcegraph Cody.
Give it your machines.

Q: How do I connect Sourcegraph Cody to AI Commander?

Cody supports local (stdio) MCP servers via the cody.mcpServers setting. In VS Code settings.json or JetBrains cody_settings.json, add an entry that runs npx -y @aicommander/mcp with AICOMMANDER_SERVER=https://aicommander.dev. You can also open Cody → MCP Settings in the extension UI and paste the same command/args/env. Enable agentic MCP context if your Sourcegraph instance gates it behind a feature flag. First connect may open a one-time browser sign-in (OAuth). For account aliases, set AICOMMANDER_TOKEN in env. See /howto/ for the full matrix.

AI Commander is not an alternative to Sourcegraph Cody, GitHub Copilot, Claude Code, Codex, ChatGPT, Cursor, 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.

Positioning in one line: Cody 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 · GitHub Copilot · Aider · Cline · Roo Code · Zed · OpenCode · Qwen Code · goose · Amp · Kilo Code · Continue · Windsurf · Claude Code · Grok · Codex · ChatGPT · Gemini.

Connect Cody (stdio / cody.mcpServers)

Sourcegraph Cody (agentic MCP docs) connects to local stdio MCP servers today — not raw remote HTTP. Point Cody at AI Commander’s npm stdio bridge the same way Cursor and Continue do:

VS Code settings.json — cody.mcpServers

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

JetBrains: the same object under cody.mcpServers in cody_settings.json (use an absolute path for command if needed — which npx). Or open the Cody extension → profile → MCP Settings and paste the command / args / env there.

Optional alias auth (after you sign in and create an API key):

env (optional)

"env": {
  "AICOMMANDER_SERVER": "https://aicommander.dev",
  "AICOMMANDER_TOKEN": "<your-key>"
}

Full client matrix (Cody, Copilot, Cursor, Claude Code, Codex, ChatGPT, Continue, Windsurf, Cline, Roo Code, Zed, REST): Connect your AI client. Cody MCP docs: Agentic context fetching.

First connect may open a one-time browser sign-in (OAuth Dynamic Client Registration). Enterprise Sourcegraph instances may require the agentic-context-mcp-enabled feature flag before Cody will load MCP tools. On Windows use "command": "npx.cmd".

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 Cody 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
Sourcegraph Cody	`cody.mcpServers` + `npx @aicommander/mcp`
GitHub Copilot	`copilot mcp add --transport http …` / `~/.copilot/mcp-config.json`
Kilo Code	`mcp.aicommander.url → https://aicommander.dev/mcp`
Amp	`amp mcp add aicommander https://aicommander.dev/mcp`
goose	`goose session --with-streamable-http-extension "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
Cline / Roo Code / Zed	MCP settings / `context_servers` + bridge or remote URL

FAQ

Is AI Commander an alternative to Sourcegraph Cody?

No. AI Commander is a remote-machine harness. You keep Sourcegraph Cody (or Claude Code, Codex, ChatGPT, Cursor, GitHub Copilot, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, Zed, OpenCode, Qwen Code, goose, Amp, Kilo Code) 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 Sourcegraph Cody to AI Commander?

Cody supports local (stdio) MCP servers via the cody.mcpServers setting. In VS Code settings.json or JetBrains cody_settings.json, add an entry that runs npx -y @aicommander/mcp with AICOMMANDER_SERVER=https://aicommander.dev. You can also open Cody → MCP Settings in the extension UI and paste the same command/args/env. Enable agentic MCP context if your Sourcegraph instance gates it behind a feature flag. First connect may open a one-time browser sign-in (OAuth). For account aliases, set AICOMMANDER_TOKEN in env. See /howto/ for the full matrix.

How is this different from Cody running locally only?

Local Sourcegraph Cody 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 Cody can run shell, detached jobs, and file transfer on those machines over MCP.

Next steps

Install the agent on a machine you control, connect Cody via cody.mcpServers + npx @aicommander/mcp, then ask for a real task on a remote box.

Install the agent Setup guides Remote coding agents

Keep Sourcegraph Cody.Give it your machines.