Auten MCP server
ai.auten/mcp·v0.1.5Computer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta)
not scanned yet
0 stars665 downloads/wk
Reviews
Write oneNobody has reviewed Auten yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Auten tools
No tool declarations could be read from the package source. They show once the server is installed.
How Auten compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- Downloads a week
- 665
- more than 91% of 12,191 servers with a package
Release history: 3 versions in the registry since 2026-10-08, latest 2026-10-14, typically one every 5 days.
Install Auten in Claude Code, Cursor or VS Code
Runs npx -y @autenai/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y @autenai/mcp
What the publisher says
From the Auten repository's README, as published. We do not edit it. Read it on GitHub
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 — and your Android phone (beta) — in real apps that have no API.
Website | Setup for every client | Pricing | hello@auten.ai
Illustration: the first run is driven by your AI, the next runs replay from memory.
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:
list of real buttons and fields (listelements then clickat(3)) instead of guessing coordinates. OCR and real screenshots are there when an app has no accessibility info.
- Reads the UI, not just pixels. It uses the accessibility tree, so your agent gets a numbered
it as a skill. The next run replays in seconds, with no tokens spent, and fixes itself when the app's layout changes.
- Learns a task once, replays it without AI. After your agent finishes a task, Auten can save
agent ever seeing the value.
- Passwords stay on your machine. fill_login types a stored secret into a field without the
Real capture, not an illustration: first run by the agent (~14 s incl. thinking), then run_skill with new values (4.8 s, no model call). Local test page, 1 fps, one cut between the runs.
What you can ask your agent
Plain requests in the client you already use. The agent decides the steps, Auten does the clicks.
- "Open the supplier portal, download this month's invoices and put them in ~/Invoices."
- "Go through the new leads in the CRM and fill in the missing company names from their emails."
- "Export the report from that desktop app as CSV. It has no API, so use the File menu."
- "On my Android phone, open Instagram and reply to the latest DM with this text." (phone is beta, over USB)
- "That worked. Save it as a skill called export-report." Next time: "Run export-report." It replays without AI.
Quick start
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Auten: common questions
- Is Auten MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Auten safety report
- How do I install Auten?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Auten need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Auten maintained?
- The last commit was 22 days ago (2026-10-13). The latest release is v0.1.5.
- How does Auten compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); downloads a week 665 (more than 91% of 12,191 servers with a package). Full comparison.