Keep JetBrains AI Assistant.
Give it your machines.

AI Commander is not an alternative to JetBrains AI Assistant, 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, LM Studio, Trae, Claude Desktop, n8n, OpenAI Agents SDK, Visual Studio, or Open WebUI. 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 · Trae · Claude Desktop · n8n · OpenAI Agents SDK · Visual Studio · Open WebUI · Gemini — and the rest on Connect your AI client.

Connect JetBrains AI Assistant (MCP)

JetBrains AI Assistant — in IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider and the other JetBrains IDEs — is an MCP client over stdio, Streamable HTTP, and legacy SSE (AI Assistant docs: Model Context Protocol). Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP) (or type / in the chat and choose Add Command), click Add, and paste a JSON configuration. The account-bound path is AI Commander’s stdio bridge with your API key:

{
  "mcpServers": {
    "aicommander": {
      "command": "npx",
      "args": [
        "-y",
        "@aicommander/mcp"
      ],
      "env": {
        "AICOMMANDER_SERVER": "https://aicommander.dev",
        "AICOMMANDER_TOKEN": "<your-api-key>"
      }
    }
  }
}

Create the key in the AI Commander dashboard. Set Server level to Global for this entry, so the key lives in your IDE settings rather than with a project, click OK, then Apply — the Status column shows whether it connected. The bridge needs Node.js (npx) on your PATH. Leave out AICOMMANDER_TOKEN and it runs anonymously, driving a machine by its session code.

Remote URL, no install

AI Assistant can also connect straight to a remote server by url. JetBrains’ MCP page documents that form without a sign-in flow or a header field, while AI Commander’s /mcp answers an unauthenticated request with an OAuth challenge — so for the remote form use the explicit anonymous opt-in, which drives a machine by its session code during that code’s first hour:

{
  "mcpServers": {
    "aicommander": {
      "url": "https://aicommander.dev/mcp?anonymous=1"
    }
  }
}

Already added AI Commander to Claude Desktop’s claude_desktop_config.json (the npx -y @aicommander/mcp entry)? Import from Claude on the same settings page can bring that entry over; a Claude Desktop custom connector has to be added here separately (see Keep Claude Desktop). Once connected, AI Assistant calls AI Commander tools when your request needs them, or you invoke one with / in the chat. Long builds and test runs belong in detached jobs (remote_job_start) so the chat does not wait. Connection problems? Help → Show Log in Explorer/Finder → the mcp folder has the MCP logs.

Not to be confused with Settings → Tools → MCP Server, which exposes the IDE itself as an MCP server to outside clients — AI Commander goes the other way and gives the IDE’s assistant your remote machines. Using the Junie agent? See Keep JetBrains Junie. Full client matrix (JetBrains AI Assistant, Visual Studio, Open WebUI, Junie, Claude Code, Codex, ChatGPT, Cursor, Copilot, Gemini, and more, plus REST): Connect your AI client. Settings can differ between IDE versions — check the linked AI Assistant 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 AI Assistant 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