UI-TARS Desktop is part of a multimodal AI agent stack that uses vision and graphical interfaces to operate computers and web browsers. Its desktop application provides local and remote computer and browser operators, while the related Agent TARS project offers terminal and web interfaces for multimodal agents. Catalogue entries connect agent workflows and MCP tools to this stack.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bytedance/UI-TARS-desktopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/bytedance/ui-tars-desktop/template-default-mcp-server-browser)<a href="https://agentmods.dev/mcp/bytedance/ui-tars-desktop/template-default-mcp-server-browser"><img src="https://agentmods.dev/badge/mcp/bytedance/ui-tars-desktop/template-default-mcp-server-browser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/bytedance/ui-tars-desktop/template-default-mcp-server-browser"><img src="https://agentmods.dev/badge/mcp/bytedance/ui-tars-desktop/template-default-mcp-server-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-server-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"mcp-server-browser": {
"command": "npx",
"args": [
"-y",
"@agent-infra/mcp-server-browser"
],
"env": {
"DISPLAY": ""
}
}
}What else server.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 12 lines scan A dc060e9a1453
mcp-server-browser is an MCP server published in the GitHub repository bytedance/UI-TARS-desktop (39,288 stars, last pushed 7d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
axstream
Fast, verified computer use for agents: a streaming JSONL action spec, a verified click ladder, and macros that make repeat tasks instant. Runs locally from the axstream Python package.
open-compute-mcp
Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting. Runs locally from the open-compute-mcp npm package.
hermes-computer-use
Pixel-level browser automation MCP server for WSL2 — drive a real Chrome with screenshot + xdotool, no CDP. Runs locally from the hermes-computer-use Python package.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
postman-mcp-server
A basic MCP server to operate on the Postman API. Runs locally from the @postman/postman-mcp-server npm package. Needs 1 environment variable to run.
vessel-browser
AI-native browser runtime for autonomous agents with human-in-the-loop supervision. Runs locally from the @quanta-intellect/vessel-browser npm package.