作者 bytedance · bytedance/UI-TARS-desktop
ByteDance's open multimodal agent stack — vision-grounded computer-use, callable from Claude via MCP.
UI-TARS Desktop is ByteDance's open multimodal agent platform. It uses screen understanding for desktop control and exposes itself as MCP. Claude can delegate vision-grounded GUI tasks where text-only tools fall short.
%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"ui-tars-desktop-mcp": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
}
}開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。
{
"mcpServers": {
"ui-tars-desktop-mcp": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
}
}Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。
{
"mcpServers": {
"ui-tars-desktop-mcp": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
}
}點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。
{
"mcpServers": {
"ui-tars-desktop-mcp": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
}
}格式與 Claude Desktop 相同。重啟 Windsurf 生效。
{
"mcpServers": [
{
"name": "ui-tars-desktop-mcp",
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
]
}Continue 使用伺服器物件陣列，而非映射。
{
"context_servers": {
"ui-tars-desktop-mcp": {
"command": {
"path": "docker",
"args": [
"run",
"-p",
"8080:8080",
"ghcr.io/bytedance/ui-tars-desktop:latest"
]
}
}
}
}加入 context_servers。Zed 儲存後熱重載。
claude mcp add ui-tars-desktop-mcp -- docker run -p 8080:8080 ghcr.io/bytedance/ui-tars-desktop:latest一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。
何時使用： You're automating a desktop or canvas app that has no scripting surface.
結果： GUI automation in apps with no API.
UI-TARS for vision tasks; OpenAgent for code-text tasks
| 工具 | 輸入參數 | 何時呼叫 | 成本 |
|---|---|---|---|
| ui_act | (see docs) | Run a vision-grounded GUI action | 1 call |
| ui_observe | (see docs) | Capture screen state | 1 call |
screen-capture input-injectionRun with banking app visibleAction misses target on Retina displaySet the DPI scale; UI-TARS defaults to 1x
| 替代方案 | 何時用它替代 | 權衡 |
|---|---|---|
| OpenAgent | Lower resource cost | Less vision grounding |