Gemini

Google's Gemini CLI as an in-editor agent. Free tier available, but performance lags other agents — see Choosing an Agent before committing.

Gemini CLI is Google’s terminal coding agent with a generous free tier. It runs as an in-editor agent through ACP. There is no marketplace plugin path for Gemini — for driving the editor from a terminal, use Claude Code CLI or ChatGPT Codex CLI.

Requires NeoStack AI plugin 3.1.8 or newer.

Video tutorial

Setup

1. Install Gemini CLI:

   npm install -g @google/gemini-cli

2. Authenticate using one of:
   • Google account — run gemini and sign in when prompted
   • API key — set GEMINI_API_KEY environment variable
   • Vertex AI — set GOOGLE_CLOUD_PROJECT and GOOGLE_APPLICATION_CREDENTIALS
3. Open Agent Chat in Unreal and select Gemini CLI from the dropdown.

The plugin launches Gemini with the --acp flag and passes the editor connection automatically via the ACP session/new request — no manual MCP configuration needed.

Standalone Gemini CLI (outside the editor)

To use Gemini CLI in a terminal outside the editor’s chat panel, connect it through the NeoStack bridge, a small stdio MCP binary that finds the running editor automatically.

Download the bridge

On macOS/Linux, run chmod +x on it once.

Via CLI command

gemini mcp add unreal /path/to/neostack-bridge-macos-arm64

Manual configuration

Add this to ~/.gemini/settings.json (Linux/macOS) or %APPDATA%\gemini\settings.json (Windows):

{
  "mcpServers": {
    "unreal": {
      "command": "/path/to/neostack-bridge-macos-arm64"
    }
  }
}

There are no ports, tokens, or URLs to configure. The bridge finds the running editor and follows restarts. If several editors are open, ask the agent to “list unreal projects” and “select” one, or set the NEOSTACK_PROJECT_DIR env var in the server config.

Features

• Multiple Gemini models (2.5 Pro, 2.5 Flash, 2.5 Flash Lite, 3 Pro Preview, 3 Flash Preview)
• Model is selected at launch time — use the model dropdown in the chat panel before starting a session
• Web search and URL context tools
• Sandbox execution environment

Custom path

If your Gemini CLI installation is in a non-standard location, set the path in Project Settings → Plugins → NeoStack AI → Gemini CLI Path.

Troubleshooting

Reset MCP configuration (standalone)

If you’re having persistent connection issues with standalone Gemini CLI:

gemini mcp remove unreal
gemini mcp add unreal /path/to/neostack-bridge-macos-arm64

Debug mode

gemini --log-level debug