
Auten
ai.autenv0.1.1Updated Oct 6, 2026
Computer use for Claude Code, Codex, Cursor or any MCP client on Mac, Windows and Linux.
Overview
Lets an AI agent control a Mac, Windows or Linux desktop by reading the accessibility tree and clicking, typing and filling fields in real apps.
- What it does
- Auten is a local runner that exposes computer-use tools to any MCP client. Tools cover seeing the screen (list_elements, read_text, screenshot, vision), acting (click_at, fill, type, press_keys, scroll, drag, menu_select), managing apps and windows (open_app, open_url, focus_window, browser_tabs, save_file, upload_file, clipboard_read), stored logins (list_logins, fill_login, get_profile) and learned skills that can be recorded and replayed without the model. It reads the accessibility tree so the agent gets a numbered list of real buttons and fields rather than guessing coordinates, with OCR and screenshots as fallback.
- When to use it
- Useful when an assistant needs to operate desktop applications that have no API, such as exporting a design frame, filling a form, or moving data between a mail client and an accounting app. Also relevant if you want repeatable GUI tasks recorded once and replayed cheaply.
- Requirements
- A local runner installed on the machine to be controlled (macOS, Windows 10/11 or Linux X11; Android over USB in beta). The MCP side is started as a local stdio process, either the installed auten mcp-bridge command or the npm launcher @autenai/mcp via npx, so Node.js is needed for the npx route. A free account key is requested on first run; paid plans raise the monthly runtime allowance. Remote SSE use requires a personal MCP URL from the account page.
Installation
In SourceWeft
- Open Auten in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
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.
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_elementsthenclick_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_logintypes a stored secret into a field without the agent ever seeing the value.
Quick start
1. Install the runner (one command, no admin rights):
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:
or add it with the Claude Code CLI and check with /mcp:
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.
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
or in ~/.codex/config.toml:
Cursor
~/.cursor/mcp.json (or .cursor/mcp.json in a project):
Gemini CLI
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):
Restart Claude Desktop.
VS Code (GitHub Copilot agent mode)
Run MCP: Open User Configuration and add:
Windsurf
~/.codeium/windsurf/mcp_config.json:
Zed
~/.config/zed/settings.json:
Cline
MCP Servers, Configure (cline_mcp_settings.json):
Remote (SSE) instead of stdio
For clients that connect over the network, keep the runner online on the computer it should control:
Then use your personal MCP URL from your account page. It contains your key, so keep it private.
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
Platforms
macOS (Apple Silicon and Intel), Windows 10/11, Linux (X11), plus an Android phone over USB (beta).
Pricing
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.
Source: README.md at commit fb9851a
Tools
0Version history
1- v0.1.1LatestOct 6, 2026


