Agentfenster
Windows GUI automation on a hidden second desktop, driven from Claude Code over MCP.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
Manual Client & Custom JSON ConfigExpand JSON ▾
Install Config Generator
Choose your client
💡 Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Documentation Overview
agentfenster MCP server
The agentfenster MCP server lets Claude Code and other MCP clients drive real Windows applications on a hidden second desktop inside your own session, with the same logins, cookies and VPN, while you keep your screen, mouse and keyboard. It is a local stdio server with 11 tools, from a one call task loop down to single verified clicks.
Every action is verified against the window state afterwards. A click that lands nowhere is reported as a failure, never as a silent success.
Full documentation: https://agentfenster.com/mcp
The MCP server ships with the agentfenster app, a commercial closed-source Windows product. This repository is its public documentation and issue tracker. It contains no product source code.
Install
- Install agentfenster on Windows 10 or 11 from https://agentfenster.com. The MCP server is part of the app. Every plan starts with a 3-day trial, no card and no account required.
- Register the server with Claude Code:
Any MCP client that can launch a local stdio server works the same way. Then just ask:
The 11 tools
| Tool | What it does |
|---|---|
list_windows | Lists the windows this machine can drive, with title, class, minimized state and whether a picture can be captured. The starting point when you do not know the exact window title. |
desktop_task | Runs a full GUI task in one window and returns a single paragraph: what happened, whether it worked, and if not, which step failed and why. The click loop runs inside the server, so its retries never enter your context. |
inspect_window | Returns the capped, filtered element tree of one window as a compact list, for planning clicks yourself. Capped at 200 elements and never walked from the desktop root. |
replay | Lists recent runs, or returns one run's step-by-step log: every plan, every action, whether it changed anything, and a link to the visual replay in the app. |
open_app | Launches a program on the shared agent desktop and reports its first titled window. The agent desktop starts empty, so this is how anything gets onto it. |
read_desktop | Reads the compact element tree of a window on the agent desktop, one line per interactive element, no screenshot. Plan your clicks from this. |
click | Clicks one element, chosen by id or name from read_desktop, then verifies against the desktop state and states explicitly whether anything changed. |
type_text | Types text into one element on the agent desktop, then verifies whether anything changed. |
press_key | Presses a key or key combination such as ctrl+s, enter, tab or alt+f4, optionally focusing an element first, with verification afterwards. |
scroll | Scrolls a window or a specific pane and reports whether the content actually moved. A list that is already at the bottom reports no effect. |
agent_windows | Lists the windows currently open on the shared agent desktop, frontmost first, so you can pick one by a title substring. |
How it works
- The agent works on a second Win32 desktop inside your session. It never takes your foreground, mouse or keyboard, and you can watch it live in the app.
- Tools read the UI Automation element tree instead of screenshots: one line per interactive element, capped at 200 elements per window.
- The click loop of
desktop_taskruns inside the server on a model endpoint you configure, so its retries and intermediate steps never enter your context. - Risky actions such as delete, send, pay or install are denied by default on MCP calls and reported, instead of blocking on a confirmation nobody can answer.
- agentfenster sends no telemetry. The only network traffic is the model endpoint you configure for the click loop.
Requirements
| Platform | Windows 10 or 11 |
| Transport | stdio, local |
| Runtime | Python 3.11 or newer, installed with the app |
| Prerequisite | the agentfenster app (commercial, 3-day trial) |
Links
- Product and download: https://agentfenster.com
- MCP documentation: https://agentfenster.com/mcp
- Pricing: https://agentfenster.com/#pricing
- Discord: https://discord.gg/J9MfKP255Y
- Support: hello@agentfenster.com
- Privacy: https://agentfenster.com/privacy
- Terms: https://agentfenster.com/terms
Issues
Use the issue tracker of this repository for bug reports and questions about the MCP server: tool behaviour, install problems, MCP client compatibility. For anything about the app itself, Discord and hello@agentfenster.com are faster.
Rights
agentfenster is commercial closed-source software. No open-source license is granted here. The text in this repository is published so that MCP users and directories can read, quote and link to it. Use of the agentfenster app itself is governed by the terms at https://agentfenster.com/terms.
Related MCP Servers
Frequently Asked Questions about Agentfenster
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/agentfenster)HTML Embed
<a href="https://allmcps.com/mcp/agentfenster"><img src="https://allmcps.com/api/badge/agentfenster?style=directory" alt="Agentfenster on AllMCPs" /></a>Technical Specs & Signals
CategoryDeveloper Tools
40Quality signal: Fair · 40/100How this signal is calculated ▾
Server availabilityNot measured
Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.
Verified ownership10/20
Documentation & tools16/30
Adoption & activity4/15
Community engagement0/10
A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.
Own this project?
This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge.
Free dofollow backlink: after claiming, verify your product site and place a dofollow AllMCPs badge — we recheck it stays live.
Claim & get free dofollowShare & Embed
Add our SVG badge (dark/light directory styles) or embeddable widget to your site.