# UI-TARS Browser MCP

> ByteDance's local MCP server that lets your agent drive a real browser: open pages, click, fill in forms, read pages and take screenshots.

ByteDance's browser automation MCP server, from its UI-TARS Desktop repository and published on npm as @agent-infra/mcp-server-browser. It drives a browser with Puppeteer and gives your agent the page as structured accessibility data and numbered clickable elements rather than pixels, so it works without a vision model. An optional vision mode adds screenshots and coordinate clicks for complex layouts.

What you can do with it
- Open pages, go back and forward, and open, switch and close tabs
- List the clickable elements on a page, then click, hover, select options and fill in form fields
- Press keys and scroll
- Read a page as text or Markdown, and collect its links
- Take screenshots of the whole page or a single element
- Run JavaScript in the page
- See downloaded files and the browser's console logs

How it connects
It runs on your machine with npx @agent-infra/mcp-server-browser@latest and needs Node.js 18 or newer. ByteDance documents setup for VS Code with GitHub Copilot, Cursor, Windsurf and Claude Desktop. It opens a visible browser by default: pass --headless to hide it, --browser to pick Chrome, Edge or Firefox, or --cdp-endpoint or --ws-endpoint to drive a browser that's already running. Start it with --port to serve it over Streamable HTTP or SSE instead of stdio.

Good to know
- Add --vision to work from screenshots and coordinate clicks instead of accessibility snapshots.
- Other options set a proxy, user agent, viewport size, user data directory and output folder.
- It needs no account or API key, but it acts in the browser with whatever sessions that browser holds, and its browser_evaluate tool runs any JavaScript on the page.

- Type: Plugin
- Made by: bytedance
- Category: Web & browser
- Formats: Local MCP
- Version: 1.0.0
- Website: https://github.com/bytedance/UI-TARS-desktop/tree/main/packages/agent-infra/mcp-servers/browser
- Source: https://github.com/bytedance/ui-tars-desktop/tree/HEAD/packages/agent-infra/mcp-servers/browser
- Page: https://pluginboard.ai/plugins/ui-tars-browser-mcp

## Works with

- Claude
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- OpenClaw
- OpenCode
- Hermes Agent

## Install

You'll need:

- `DISPLAY` (optional): DISPLAY environment variable for browser rendering

Replace each `<NAME>` placeholder with your own value.

### Claude

Add to claude_desktop_config.json:

```json
{
  "mcpServers": {
    "ui-tars-browser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/mcp-server-browser@latest"
      ]
    }
  }
}
```

### GitHub Copilot

Add to VS Code: vscode:mcp/install?%7B%22name%22%3A%22ui-tars-browser-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40agent-infra%2Fmcp-server-browser%40latest%22%5D%7D

Run in your terminal:

```shell
code --add-mcp '{"name":"ui-tars-browser-mcp","command":"npx","args":["-y","@agent-infra/mcp-server-browser@latest"]}'
```

Copilot CLI:

```shell
copilot mcp add ui-tars-browser-mcp -- npx -y @agent-infra/mcp-server-browser@latest
```

### Cursor

Add to Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=ui-tars-browser-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBhZ2VudC1pbmZyYS9tY3Atc2VydmVyLWJyb3dzZXJAbGF0ZXN0Il19

Add to .cursor/mcp.json:

```json
{
  "mcpServers": {
    "ui-tars-browser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/mcp-server-browser@latest"
      ]
    }
  }
}
```

### Claude Code

Run in your terminal:

```shell
claude mcp add ui-tars-browser-mcp -- npx -y @agent-infra/mcp-server-browser@latest
```

### Codex

Run in your terminal:

```shell
codex mcp add ui-tars-browser-mcp -- npx -y @agent-infra/mcp-server-browser@latest
```

### Antigravity

Add to ~/.gemini/config/mcp_config.json:

```json
{
  "mcpServers": {
    "ui-tars-browser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/mcp-server-browser@latest"
      ]
    }
  }
}
```

### Gemini CLI

Run in your terminal:

```shell
gemini mcp add ui-tars-browser-mcp npx -y @agent-infra/mcp-server-browser@latest
```

### OpenClaw

In a terminal: Run openclaw mcp add ui-tars-browser-mcp --command npx, with --arg before each argument (-y @agent-infra/mcp-server-browser@latest) and --env NAME=value for each variable it needs.

### OpenCode

Run in your terminal:

```shell
opencode mcp add ui-tars-browser-mcp -- npx -y @agent-infra/mcp-server-browser@latest
```

### Hermes Agent

Add to ~/.hermes/config.yaml:

```json
{
  "mcp_servers": {
    "ui-tars-browser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/mcp-server-browser@latest"
      ]
    }
  }
}
```

---
From Pluginboard (https://pluginboard.ai).