Auten

ai.autenv0.1.1更新于 Oct 6, 2026

Computer use for Claude Code, Codex, Cursor or any MCP client on Mac, Windows and Linux.

概览

AI 生成的概览

让 AI 助手通过读取无障碍树并点击、输入、填写字段来控制 Mac、Windows 或 Linux 桌面上的真实应用。

功能
Auten 是一个本地运行器,向任意 MCP 客户端提供电脑操作工具。工具涵盖查看屏幕(list_elements、read_text、screenshot、vision)、执行操作(click_at、fill、type、press_keys、scroll、drag、menu_select)、管理应用与窗口(open_app、open_url、focus_window、browser_tabs、save_file、upload_file、clipboard_read)、已保存的登录信息(list_logins、fill_login、get_profile),以及可录制并在无模型参与下重放的技能。它读取无障碍树,让助手获得真实按钮和输入框的编号列表,而不是猜测坐标,必要时回退到 OCR 和截图。
适用场景
当助手需要操作没有 API 的桌面应用时适用,例如导出设计稿、填写表单,或在邮件客户端与记账软件之间搬运数据。也适合把重复的图形界面任务录制一次后低成本重放。
运行要求
需要在被控制的机器上安装本地运行器(macOS、Windows 10/11 或 Linux X11;Android 通过 USB 为测试版)。MCP 侧以本地 stdio 进程启动,可使用已安装的 auten mcp-bridge 命令,或通过 npx 运行 npm 启动器 @autenai/mcp,后者需要 Node.js。首次运行会要求连接一个免费密钥;付费方案提高每月运行时长。远程 SSE 方式需要账户页面提供的个人 MCP URL。
安装前请注意
该服务可以点击、输入、打开应用和文件、读取剪贴板并读取屏幕,因此助手可能改动或删除它能触及的任何应用中的数据。保存的密码存放在系统钥匙串或本地保险库中,由 fill_login 输入而不让助手看到值,但个人 SSE URL 包含你的密钥,应妥善保密。屏幕内容会发送给你选择的模型提供商,免费额度为每月 30 分钟。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Auten,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[Auten: computer use MCP server]

Auten MCP server

Computer use for the AI agent you already have.
Claude Code, Codex, Cursor, Gemini CLI or any MCP client can click, type and read the screen on your Mac, Windows or Linux computer, in real apps that have no API.

[npm]

Website  |  Setup for every client  |  Pricing  |  [email protected]


Auten is the hands, your AI is the brain. A small runner on your computer does the clicking, typing and screen reading. Your agent talks to it over MCP (stdio or SSE). Auten does not ship its own model and never needs your AI key; your agent keeps using the plan you already pay for.

What makes it different from a plain mouse and keyboard bridge:

  • Reads the UI, not just pixels. It uses the accessibility tree, so your agent gets a numbered list of real buttons and fields (list_elements then click_at(3)) instead of guessing coordinates. OCR and real screenshots are there when an app has no accessibility info.
  • Learns a task once, replays it without AI. After your agent finishes a task, Auten can save it as a skill. The next run replays in seconds, with no tokens spent, and fixes itself when the app's layout changes.
  • Passwords stay on your machine. fill_login types a stored secret into a field without the agent ever seeing the value.

Quick start

1. Install the runner (one command, no admin rights):

bash
# macOS and Linuxcurl -fsSL https://auten.ai/install | bash
powershell
# Windows (PowerShell)irm https://auten.ai/install.ps1 | iex

The first run asks you to connect a free key (30 minutes every month, no card).

2. Add Auten to your agent. For Claude Code, Auten can do it by itself:

bash
auten connect

or add it with the Claude Code CLI and check with /mcp:

bash
claude mcp add -s user auten -- auten mcp-bridge

3. Ask in plain words. For example: "Open Figma, export the Hero frame as PNG to my Desktop" or "Go through the unread invoices in my mail and fill them into the accounting app".

Or run it through npx

Any client that can start an npm package can use the launcher instead. It starts the installed runner, and if Auten is not installed yet it tells your agent the one-line install command.

json
{  "mcpServers": {    "auten": { "command": "npx", "args": ["-y", "@autenai/mcp"] }  }}
bash
claude mcp add -s user auten -- npx -y @autenai/mcp

Client setup

Every client starts the same stdio command: auten mcp-bridge (or npx -y @autenai/mcp). If your app says it cannot find auten, use the full path from which auten (usually ~/.local/bin/auten).

OpenAI Codex
bash
codex mcp add auten -- auten mcp-bridge

or in ~/.codex/config.toml:

toml
[mcp_servers.auten]command = "auten"args = ["mcp-bridge"]
Cursor

~/.cursor/mcp.json (or .cursor/mcp.json in a project):

json
{  "mcpServers": {    "auten": { "command": "auten", "args": ["mcp-bridge"] }  }}
Gemini CLI
bash
gemini mcp add --scope user auten auten mcp-bridge

or the same mcpServers entry in ~/.gemini/settings.json.

Claude Desktop

Settings, Developer, Edit Config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

json
{  "mcpServers": {    "auten": { "command": "auten", "args": ["mcp-bridge"] }  }}

Restart Claude Desktop.

VS Code (GitHub Copilot agent mode)

Run MCP: Open User Configuration and add:

json
{  "servers": {    "auten": { "type": "stdio", "command": "auten", "args": ["mcp-bridge"] }  }}
Windsurf

~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "auten": { "command": "auten", "args": ["mcp-bridge"] }  }}
Zed

~/.config/zed/settings.json:

json
{  "context_servers": {    "auten": { "command": "auten", "args": ["mcp-bridge"] }  }}
Cline

MCP Servers, Configure (cline_mcp_settings.json):

json
{  "mcpServers": {    "auten": { "command": "auten", "args": ["mcp-bridge"] }  }}
Remote (SSE) instead of stdio

For clients that connect over the network, keep the runner online on the computer it should control:

bash
auten --runner-only

Then use your personal MCP URL from your account page. It contains your key, so keep it private.

bash
claude mcp add --transport sse auten <your-url>

No agent? Give the auten CLI your own key (Anthropic, OpenAI, Google, DeepSeek or any OpenAI-compatible provider) with auten key add, then run auten "open my calendar and tell me what is next".

Tools

GroupTools
See the screenlist_elements, read_text, screenshot, screenshot_labeled, vision, screen_info
Actclick_at, click, fill, type, paste_text, press_keys, scroll, drag, move_mouse, act_on_matching, menu_select
Apps and windowsopen_app, open_url, focus_window, browser_tabs, save_file, upload_file, clipboard_read
Secretslist_logins, fill_login, get_profile
Learned skillslist_skills, run_skill, skills, show_skill, start_recording, stop_recording, start_fixing, stop_fixing
Coordinationask_user, focus_app, release, gui_status, wait, opened_items, browser_cleanup

Platforms

macOS (Apple Silicon and Intel), Windows 10/11, Linux (X11), plus an Android phone over USB (beta).

Pricing

PlanRuntimePrice
Free30 min every month€0, no card
Starter10 h every month€9/month (early access)
ProUnlimited€29/month (early access)

You bring your own AI, so the price is for Auten only. Details on auten.ai/pricing.

Privacy and safety

  • The runner only acts when your MCP client calls a tool. Nothing runs in the background on its own.
  • Stored passwords live in the system keychain (macOS, Windows) or a private local vault (Linux) and never reach our servers or the model. A secret that shows up on screen is replaced with a placeholder before your agent sees it.
  • Your activity history and learned skills are written to your own computer, not ours. See the privacy policy.

About this repository

This repository holds the public docs, client configs and the @autenai/mcp npm launcher (bin/auten-mcp.js, MIT). The runner itself is distributed through the installers above. Questions, bugs and feature requests are welcome as issues or at [email protected].

Auten is made by MB Icecode, Lithuania.

来源:README.md,提交 fb9851a

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v0.1.1最新Oct 6, 2026