Computer Use MCP server

Q: Wie füge ich Computer Use MCP zu Claude Code hinzu?

Führe `claude mcp add computer-use -- npx -y munim-computer-use` in deinem Terminal aus. Füge `--scope user` hinzu, damit der Server in jedem Projekt verfügbar ist.

Q: Wie füge ich Computer Use MCP zu Cursor hinzu?

Öffne `~/.cursor/mcp.json` und füge den Server unter `mcpServers` hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.

✓ VerifiziertCommit 8. Nov. 2026

munimtechnologies/computer-use · rust · Apache-2.0

Lass KI-Agenten deinen Desktop steuern, indem sie Accessibility Trees lesen und Hintergrund-Inputs auf macOS, Windows und Linux ausführen.

Auch bekannt als munimtechnologies/computer-use, computer-use, munim-computer-use

stdio 2 Tools Workflow Automation

Installieren GitHub ↗

Stars: 38
Tools: 2
Downloads, 30 Tage: —
Neueste Version: 0.1.0
Letzter Commit: 8. Nov. 2026
Lizenz: Apache-2.0

Was ist Computer Use MCP?

Computer Use ist ein MCP server. Lass KI-Agenten deinen Desktop steuern, indem sie Accessibility Trees lesen und Hintergrund-Inputs auf macOS, Windows und Linux ausführen. Er stellt 2 Tools bereit, etwa wait_timeout_ms, readiness.

Zusammenfassung generiert aus dem README des Projekts

Über Computer Use MCP server

Entwickler können KI-Agenten mit diesem MCP server direkte Kontrolle über ihre Desktop-Umgebungen geben. Er fungiert als Backend für Computer-Use-Agenten, das es Coding-Agenten ermöglicht, mit macOS-, Windows- und Linux-Systemen so zu interagieren, wie es ein Mensch tun würde. Durch das Lesen von Accessibility Trees zur Identifizierung spezifischer Element-IDs ermöglicht der Server Agenten das Klicken und Tippen, ohne für jede Interaktion ein Vision-Modell zu benötigen.

Ein herausragendes Feature ist die Fähigkeit, Hintergrund-Inputs auszuführen. Das bedeutet, dass der Agent im Hintergrund arbeiten kann, sodass deine physische Maus und Tastatur für deine eigene Nutzung verfügbar bleiben. Der Server arbeitet mit verschiedenen MCP Clients wie Claude Code, Codex, Cursor und MT Code zusammen. Das Setup umfasst das Herunterladen der plattformspezifischen Binary und das Registrieren beim gewählten Agenten über die Command Line oder Config-Dateien. Er bietet Tools, um App-States abzurufen, über Element-IDs zu agieren und Aktionen durch Screenshots zu verifizieren.

Was du damit machen kannst

1Automatisierung von App-übergreifenden WorkflowsEin KI-Agent kann einen Webbrowser öffnen, um spezifische Informationen zu finden, und diese Daten anschließend in eine lokale Notiz-App übertragen.
2Desktop-Aufgaben im Hintergrund ausführenDu kannst einen Agenten Aufgaben auf deinem Computer ausführen lassen, während du deine Maus und Tastatur für andere Arbeiten weiter nutzt.
3Präzise UI-Interaktion via Element-IDsAnstatt Pixel-Koordinaten zu raten, kann ein Agent über Accessibility-Daten direkt mit spezifischen Buttons und Steuerelementen interagieren.

Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.

So installierst du Computer Use MCP

Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügen Zu Goose hinzufügen

Claude CodeCursorVS CodeVS Code CLIClaude DesktopCodexCodex config.tomlGemini CLIGemini settings.json

$ claude mcp add computer-use -- npx -y munim-computer-use

~/.cursor/mcp.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "computer-use": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

$ code --add-mcp '{"name":"computer-use","type":"stdio","command":"npx","args":["-y","munim-computer-use"]}'

claude_desktop_config.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

$ codex mcp add computer-use -- npx -y munim-computer-use

~/.codex/config.toml

[mcp_servers.computer-use]
command = "npx"
args = ["-y", "munim-computer-use"]

$ gemini mcp add -s user computer-use npx -- -y munim-computer-use

~/.gemini/settings.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

Setze 2 Umgebungsvariablen vor dem Start des Servers (siehe unten).Setup-Anleitungen:Claude Code Cursor VS Code Claude Desktop

Computer Use MCP tools 2

Erkannt aus dem README

wait_timeout_ms
readiness

wait_timeout_ms	—
readiness	—

Konfiguration

COMPUTER_USE_AGENT_CURSOR
Set to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSER
Set to 0 to hide the browser_* tools

Name	Beschreibung	Typ
COMPUTER_USE_AGENT_CURSOR	Set to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSER	Set to 0 to hide the browser_* tools

Automatisierte Checks

Geluften am 12. Nov. 2026Vollständiger Bericht →

100/100

Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren

Diesen Score in deinem README anzeigen

Source Repository verknüpft und erreichbarBestanden
Open Source Lizenz (OSI)Bestanden
Commit oder Release im letzten JahrBestanden
Package-Name ähnelt keinem populären PackageBestanden
Remote Endpoint nutzt HTTPSNicht geprüft
Destruktive Tools sind markiertBestanden
Keine versteckten Anweisungen an das ModellBestanden
Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden

README

Auf GitHub ansehen

Introduction

Computer Use is an open-source MCP server — a computer-use agent (CUA) backend — that lets any coding agent use your computer the way a person does. It reads the screen through accessibility trees, clicks and types in the background so your mouse stays yours, shows an agent pointer where it is working, zooms in on small text, and drives tabs in your signed-in Chrome — on macOS, Windows and Linux.

Works with Claude Code, Codex, Cursor and MT Code, or any other MCP client, with any model — no vision model is required for interaction.

Built by Munim Technologies as the Computer Use engine of MT Code, and published here on its own.

Quick start
Capability matrix
Benchmarks
Why it works well
Works alongside you
Apps and sites the agent may use
Tools
Repository layout
Environment flags
Embedding in an app
Prompting your agent
Contributing
Credits and license

Quick start

Download the latest binary for your platform from Releases (munim-computer-use-macos-universal.zip, munim-computer-use-windows-x64.zip) or build from source.
Put it somewhere on your PATH (/usr/local/bin/munim-computer-use, or %LOCALAPPDATA%\Programs\munim-computer-use\munim-computer-use.exe).
macOS only: run munim-computer-use request-permissions once to be prompted for Accessibility and Screen Recording.
Register it with your agent:

# Claude Code — fastest: the npm launcher fetches the signed binary on first run.
# Add `--scope user` to register it for every project instead of just this one.
claude mcp add munim-computer-use -- npx -y munim-computer-use
# or point at a downloaded binary
claude mcp add munim-computer-use -- /usr/local/bin/munim-computer-use

# Codex — writes the entry below into ~/.codex/config.toml for you (needs a Codex CLI
# with `codex mcp`; check with `codex mcp --help`)
codex mcp add munim-computer-use -- npx -y munim-computer-use

# Codex — ~/.codex/config.toml, if you would rather edit it yourself
[mcp_servers.munim-computer-use]
command = "npx"
args = ["-y", "munim-computer-use"]

# Cursor — no MCP subcommand in its CLI, so write the config. ~/.cursor/mcp.json applies
# to every project; .cursor/mcp.json in a repo applies to that one.
mkdir -p ~/.cursor && [ -s ~/.cursor/mcp.json ] || echo '{}' > ~/.cursor/mcp.json
jq '.mcpServers["munim-computer-use"] = {"command":"npx","args":["-y","munim-computer-use"]}' \
  ~/.cursor/mcp.json > ~/.cursor/mcp.json.tmp && mv ~/.cursor/mcp.json.tmp ~/.cursor/mcp.json

// Cursor — the entry that produces, in .cursor/mcp.json
{ "mcpServers": { "munim-computer-use": { "command": "npx", "args": ["-y", "munim-computer-use"] } } }

Then ask: "Open Safari, find the cheapest flight to Denver on Tuesday and put it in a note." The agent reads the UI with get_app_state, acts by element id, and verifies with screenshot.

Capability matrix

Munim Computer Use is the highlighted first column; the others are the computer-use servers people reach for. each cell comes from that project's own README or docs in September and October 2026 (sources under Credits and license). ✅ present · ❌ absent or not documented · ⚠️ partial.

Capability	Munim Computer Use	Cua Driver	Codex Computer Use	OpenAI Agents API	Anthropic reference demo	Windows-MCP	MacOS-MCP	open-computer-use	computer-use-mcp (zavora)	Notes
macOS	✅	✅	✅	n/a	❌	❌	✅	✅	✅	The Anthropic demo drives a Linux desktop inside Docker, not your machine. The OpenAI Agents API (September 2026) runs a browser OpenAI hosts, so it never drives your machine either.
Windows	✅	✅	✅	n/a	❌	✅	❌	✅	✅	Windows-MCP is Windows only; MacOS-MCP is macOS only.
Linux	✅	✅	❌	n/a	✅ (sandbox)	❌	❌	✅	✅	Munim Computer Use uses AT-SPI + X11; native Wayland apps get element actions but not coordinate clicks.
Accessibility tree with element ids	✅	✅	⚠️	❌	❌	✅	✅	✅	✅	Codex reads the accessibility tree first on macOS and works from screenshots on Windows; the Agents API and the Anthropic demo are screenshot-driven. Ids let the agent press the button instead of a pixel.
Background input (your mouse never moves)	✅	✅	⚠️	n/a	n/a	❌	❌	❌	❌	Munim Computer Use addresses events to the target window: always on macOS (SkyLight and per-process events), for UI Automation patterns and classic Win32 controls on Windows; other Windows UI and all Linux pointer input (XTEST) still move the real pointer. Codex works in the background on macOS with cursors of its own, and takes over the pointer on Windows. Cua Driver delivers in the background by default and falls back to the foreground when that does not land. The other servers in this table drive the real cursor.
Agent pointer overlay	✅	✅	✅	❌	❌	⚠️	❌	❌	❌	Windows-MCP flashes a border around captures; Codex and Cua Driver draw their own cursor on your screen.
Zoom into a region at full resolution	✅	✅	❌	❌	✅	❌	❌	❌	❌	Anthropic's toolset has `zoom`; here it is a tool on every platform.
Screenshots carry screen-coordinate mapping	✅	⚠️	n/a	n/a	n/a	❌	❌	❌	❌	Origin and pixels-per-point in every capture, so clicks from Retina or downscaled images land.
Hover, wait, label query	✅	⚠️	⚠️	❌	⚠️	✅	⚠️	❌	⚠️	Windows-MCP has Wait/WaitFor; MacOS-MCP has Wait; Anthropic has `wait`/`mouse_move`.
Your signed-in Chrome, own tab group or yours	✅	⚠️	⚠️	❌	❌	⚠️	❌	❌	❌	Codex uses its in-app browser; Cua Driver attaches to a browser over CDP; Windows-MCP reads the DOM of open browsers. Munim Computer Use opens its own labelled tab group in your real Chrome, and can also take over a tab you already have open when you ask it to.
Act and observe in one call	✅	✅	n/a	n/a	✅	❌	❌	❌	❌	`return_state` on any action appends the fresh accessibility tree or page snapshot, so one call acts and checks. Cua Driver's `run_steps` runs several actions and reports what changed. The Anthropic demo returns a screenshot after each action; Codex and the Agents API run the loop themselves.
Several actions in one call	✅	✅	n/a	n/a	❌	⚠️	❌	❌	✅	Cua Driver and computer-use-mcp (zavora) run a list of steps in one call with `run_steps`; Windows-MCP's `MultiSelect` and `MultiEdit` act on several elements at once. Munim Computer Use's `run_steps` does the same, checks the whole list before running any of it, and stops at the first failure.
Read a page's text in a signed-in tab	✅	⚠️	❌	❌	❌	⚠️	❌	❌	❌	`browser_read` returns the page as text with headings, in chunks, with a `query` filter, from a background tab. Windows-MCP scrapes pages.
Sign-in without the model seeing the password	✅	❌	❌	✅	❌	❌	❌	❌	❌	`browser_request_credentials` opens a Chrome window naming the site's real origin; what the user types goes into the page and never into the conversation. The Agents API hands sign-in to the developer's app the same way. Desktop password fields refuse typing by default.
Per-app and per-site allow / ask / block rules	✅	❌	⚠️	⚠️	❌	❌	❌	❌	❌	A policy file the user controls; `ask` shows an approval prompt once per task. Codex asks before each new app and keeps an "Always allow" list; the Agents API asks the developer's app before each new website.
Works with any MCP client	✅	✅	❌	❌	❌	✅	✅	✅	✅	Codex Computer Use is Codex only; the Anthropic demo is Claude only.
Identical tool surface on every platform	✅	⚠️	n/a	n/a	n/a	n/a	n/a	⚠️	✅	38 tools with byte-identical schemas across the Swift and Rust servers. Cua Driver keeps shared parameters in step with a CI check, with a few tools on one platform only.
Prebuilt signed binaries + npm launcher	✅	✅ (script)	✅	n/a	❌	❌	❌	✅ (npm)	✅ (npm)	macOS universal (Developer ID signed) and Windows x64 on Releases.
Open source	✅ Apache-2.0	✅ MIT	❌	❌	✅	✅ MIT	✅ MIT	✅ MIT	✅ MIT

Also looked at: mediar-ai/mcp-server-macos-use (macOS, accessibility, real input), deploymenttheory/windows-mcp-server (Windows, UIA Invoke patterns, WaitFor), nuphus-mcp (OCR + bring-your-own vision model, CDP Chrome), computer-control-mcp (PyAutoGUI + OCR), and microsoft/playwright-mcp (browser only). Corrections welcome — open an issue with a link.

The chart counts the table above (n/a cells are left out), so

Vollständiges README lesen

Computer Use MCP Fragen

Wie füge ich Computer Use MCP zu Claude Code hinzu?

Führe claude mcp add computer-use -- npx -y munim-computer-use in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.

Wie füge ich Computer Use MCP zu Cursor hinzu?

Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.

Welche Tools bietet Computer Use MCP?

Er stellt 2 Tools bereit, darunter wait_timeout_ms, readiness.

Wird der Agent meine Maus bewegen, während er arbeitet?

Nein, er führt Hintergrund-Inputs aus, sodass deine Maus unter deiner Kontrolle bleibt.

Wie erteile ich Berechtigungen auf macOS?

Du musst den Befehl 'munim-computer-use request-permissions' ausführen, um zur Erteilung von Accessibility- und Screen Recording-Berechtigungen aufgefordert zu werden.

Fakten

14. Nov. 2026

Stars: 38
Downloads, 30 Tage: —
Neueste Version: 0.1.0
Letzter Commit: 8. Nov. 2026
Lizenz: Apache-2.0
Transport: stdio
Paket: munim-computer-use

munimtechnologies ↗

Community Publisher

Veröffentlicht von einem unabhängigen Maintainer.

Mehr von munimtechnologies →

Repository verlinkt
Open-Source-Lizenz
Aktiv in den letzten 365 Tagen

Alternativen

Skills für Computer Use

Funktioniert mit

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge für dein README

Zeige deinen HostedMCP-Checks-Score. Das Badge führt Leser zu Installationsanleitungen für jeden Client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/munimtechnologies/computer-use.svg)](https://hostedmcp.org/servers/munimtechnologies/computer-use/checks)

Maintainer?

Übernimm diesen Eintrag, um ihn zu bearbeiten und das HostedMCP-Badge zu deinem README hinzuzufügen.

Eintrag übernehmen

Vor der Installation

Server laufen mit den Berechtigungen, die du ihnen gibst. Nutze den am engsten gefassten Token oder die Datenbank-Role, die für die Aufgabe nötig ist.

Computer Use MCP server

✓ VerifiziertCommit 8. Nov. 2026

munimtechnologies/computer-use · rust · Apache-2.0

Lass KI-Agenten deinen Desktop steuern, indem sie Accessibility Trees lesen und Hintergrund-Inputs auf macOS, Windows und Linux ausführen.

Auch bekannt als munimtechnologies/computer-use, computer-use, munim-computer-use

stdio 2 Tools Workflow Automation

Installieren GitHub ↗

Stars: 38
Tools: 2
Downloads, 30 Tage: —
Neueste Version: 0.1.0
Letzter Commit: 8. Nov. 2026
Lizenz: Apache-2.0

Was ist Computer Use MCP?

Zusammenfassung generiert aus dem README des Projekts

Über Computer Use MCP server

Was du damit machen kannst

1Automatisierung von App-übergreifenden WorkflowsEin KI-Agent kann einen Webbrowser öffnen, um spezifische Informationen zu finden, und diese Daten anschließend in eine lokale Notiz-App übertragen.
2Desktop-Aufgaben im Hintergrund ausführenDu kannst einen Agenten Aufgaben auf deinem Computer ausführen lassen, während du deine Maus und Tastatur für andere Arbeiten weiter nutzt.
3Präzise UI-Interaktion via Element-IDsAnstatt Pixel-Koordinaten zu raten, kann ein Agent über Accessibility-Daten direkt mit spezifischen Buttons und Steuerelementen interagieren.

Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.

So installierst du Computer Use MCP

Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügen Zu Goose hinzufügen

Claude CodeCursorVS CodeVS Code CLIClaude DesktopCodexCodex config.tomlGemini CLIGemini settings.json

$ claude mcp add computer-use -- npx -y munim-computer-use

~/.cursor/mcp.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "computer-use": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

$ code --add-mcp '{"name":"computer-use","type":"stdio","command":"npx","args":["-y","munim-computer-use"]}'

claude_desktop_config.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

$ codex mcp add computer-use -- npx -y munim-computer-use

~/.codex/config.toml

[mcp_servers.computer-use]
command = "npx"
args = ["-y", "munim-computer-use"]

$ gemini mcp add -s user computer-use npx -- -y munim-computer-use

~/.gemini/settings.json

{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "munim-computer-use"
      ]
    }
  }
}

Setze 2 Umgebungsvariablen vor dem Start des Servers (siehe unten).Setup-Anleitungen:Claude Code Cursor VS Code Claude Desktop

Computer Use MCP tools 2

Erkannt aus dem README

wait_timeout_ms
readiness

wait_timeout_ms	—
readiness	—

Konfiguration

COMPUTER_USE_AGENT_CURSOR
Set to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSER
Set to 0 to hide the browser_* tools

Name	Beschreibung	Typ
COMPUTER_USE_AGENT_CURSOR	Set to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSER	Set to 0 to hide the browser_* tools

Automatisierte Checks

Geluften am 12. Nov. 2026Vollständiger Bericht →

100/100

Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren

Diesen Score in deinem README anzeigen

Source Repository verknüpft und erreichbarBestanden
Open Source Lizenz (OSI)Bestanden
Commit oder Release im letzten JahrBestanden
Package-Name ähnelt keinem populären PackageBestanden
Remote Endpoint nutzt HTTPSNicht geprüft
Destruktive Tools sind markiertBestanden
Keine versteckten Anweisungen an das ModellBestanden
Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden

README

Auf GitHub ansehen

Introduction

Works with Claude Code, Codex, Cursor and MT Code, or any other MCP client, with any model — no vision model is required for interaction.

Built by Munim Technologies as the Computer Use engine of MT Code, and published here on its own.

Quick start
Capability matrix
Benchmarks
Why it works well
Works alongside you
Apps and sites the agent may use
Tools
Repository layout
Environment flags
Embedding in an app
Prompting your agent
Contributing
Credits and license

Quick start

Download the latest binary for your platform from Releases (munim-computer-use-macos-universal.zip, munim-computer-use-windows-x64.zip) or build from source.
Put it somewhere on your PATH (/usr/local/bin/munim-computer-use, or %LOCALAPPDATA%\Programs\munim-computer-use\munim-computer-use.exe).
macOS only: run munim-computer-use request-permissions once to be prompted for Accessibility and Screen Recording.
Register it with your agent:

# Claude Code — fastest: the npm launcher fetches the signed binary on first run.
# Add `--scope user` to register it for every project instead of just this one.
claude mcp add munim-computer-use -- npx -y munim-computer-use
# or point at a downloaded binary
claude mcp add munim-computer-use -- /usr/local/bin/munim-computer-use

# Codex — writes the entry below into ~/.codex/config.toml for you (needs a Codex CLI
# with `codex mcp`; check with `codex mcp --help`)
codex mcp add munim-computer-use -- npx -y munim-computer-use

# Codex — ~/.codex/config.toml, if you would rather edit it yourself
[mcp_servers.munim-computer-use]
command = "npx"
args = ["-y", "munim-computer-use"]

# Cursor — no MCP subcommand in its CLI, so write the config. ~/.cursor/mcp.json applies
# to every project; .cursor/mcp.json in a repo applies to that one.
mkdir -p ~/.cursor && [ -s ~/.cursor/mcp.json ] || echo '{}' > ~/.cursor/mcp.json
jq '.mcpServers["munim-computer-use"] = {"command":"npx","args":["-y","munim-computer-use"]}' \
  ~/.cursor/mcp.json > ~/.cursor/mcp.json.tmp && mv ~/.cursor/mcp.json.tmp ~/.cursor/mcp.json

// Cursor — the entry that produces, in .cursor/mcp.json
{ "mcpServers": { "munim-computer-use": { "command": "npx", "args": ["-y", "munim-computer-use"] } } }

Then ask: "Open Safari, find the cheapest flight to Denver on Tuesday and put it in a note." The agent reads the UI with get_app_state, acts by element id, and verifies with screenshot.

Capability matrix

Capability	Munim Computer Use	Cua Driver	Codex Computer Use	OpenAI Agents API	Anthropic reference demo	Windows-MCP	MacOS-MCP	open-computer-use	computer-use-mcp (zavora)	Notes
macOS	✅	✅	✅	n/a	❌	❌	✅	✅	✅	The Anthropic demo drives a Linux desktop inside Docker, not your machine. The OpenAI Agents API (September 2026) runs a browser OpenAI hosts, so it never drives your machine either.
Windows	✅	✅	✅	n/a	❌	✅	❌	✅	✅	Windows-MCP is Windows only; MacOS-MCP is macOS only.
Linux	✅	✅	❌	n/a	✅ (sandbox)	❌	❌	✅	✅	Munim Computer Use uses AT-SPI + X11; native Wayland apps get element actions but not coordinate clicks.
Accessibility tree with element ids	✅	✅	⚠️	❌	❌	✅	✅	✅	✅	Codex reads the accessibility tree first on macOS and works from screenshots on Windows; the Agents API and the Anthropic demo are screenshot-driven. Ids let the agent press the button instead of a pixel.
Background input (your mouse never moves)	✅	✅	⚠️	n/a	n/a	❌	❌	❌	❌	Munim Computer Use addresses events to the target window: always on macOS (SkyLight and per-process events), for UI Automation patterns and classic Win32 controls on Windows; other Windows UI and all Linux pointer input (XTEST) still move the real pointer. Codex works in the background on macOS with cursors of its own, and takes over the pointer on Windows. Cua Driver delivers in the background by default and falls back to the foreground when that does not land. The other servers in this table drive the real cursor.
Agent pointer overlay	✅	✅	✅	❌	❌	⚠️	❌	❌	❌	Windows-MCP flashes a border around captures; Codex and Cua Driver draw their own cursor on your screen.
Zoom into a region at full resolution	✅	✅	❌	❌	✅	❌	❌	❌	❌	Anthropic's toolset has `zoom`; here it is a tool on every platform.
Screenshots carry screen-coordinate mapping	✅	⚠️	n/a	n/a	n/a	❌	❌	❌	❌	Origin and pixels-per-point in every capture, so clicks from Retina or downscaled images land.
Hover, wait, label query	✅	⚠️	⚠️	❌	⚠️	✅	⚠️	❌	⚠️	Windows-MCP has Wait/WaitFor; MacOS-MCP has Wait; Anthropic has `wait`/`mouse_move`.
Your signed-in Chrome, own tab group or yours	✅	⚠️	⚠️	❌	❌	⚠️	❌	❌	❌	Codex uses its in-app browser; Cua Driver attaches to a browser over CDP; Windows-MCP reads the DOM of open browsers. Munim Computer Use opens its own labelled tab group in your real Chrome, and can also take over a tab you already have open when you ask it to.
Act and observe in one call	✅	✅	n/a	n/a	✅	❌	❌	❌	❌	`return_state` on any action appends the fresh accessibility tree or page snapshot, so one call acts and checks. Cua Driver's `run_steps` runs several actions and reports what changed. The Anthropic demo returns a screenshot after each action; Codex and the Agents API run the loop themselves.
Several actions in one call	✅	✅	n/a	n/a	❌	⚠️	❌	❌	✅	Cua Driver and computer-use-mcp (zavora) run a list of steps in one call with `run_steps`; Windows-MCP's `MultiSelect` and `MultiEdit` act on several elements at once. Munim Computer Use's `run_steps` does the same, checks the whole list before running any of it, and stops at the first failure.
Read a page's text in a signed-in tab	✅	⚠️	❌	❌	❌	⚠️	❌	❌	❌	`browser_read` returns the page as text with headings, in chunks, with a `query` filter, from a background tab. Windows-MCP scrapes pages.
Sign-in without the model seeing the password	✅	❌	❌	✅	❌	❌	❌	❌	❌	`browser_request_credentials` opens a Chrome window naming the site's real origin; what the user types goes into the page and never into the conversation. The Agents API hands sign-in to the developer's app the same way. Desktop password fields refuse typing by default.
Per-app and per-site allow / ask / block rules	✅	❌	⚠️	⚠️	❌	❌	❌	❌	❌	A policy file the user controls; `ask` shows an approval prompt once per task. Codex asks before each new app and keeps an "Always allow" list; the Agents API asks the developer's app before each new website.
Works with any MCP client	✅	✅	❌	❌	❌	✅	✅	✅	✅	Codex Computer Use is Codex only; the Anthropic demo is Claude only.
Identical tool surface on every platform	✅	⚠️	n/a	n/a	n/a	n/a	n/a	⚠️	✅	38 tools with byte-identical schemas across the Swift and Rust servers. Cua Driver keeps shared parameters in step with a CI check, with a few tools on one platform only.
Prebuilt signed binaries + npm launcher	✅	✅ (script)	✅	n/a	❌	❌	❌	✅ (npm)	✅ (npm)	macOS universal (Developer ID signed) and Windows x64 on Releases.
Open source	✅ Apache-2.0	✅ MIT	❌	❌	✅	✅ MIT	✅ MIT	✅ MIT	✅ MIT

The chart counts the table above (n/a cells are left out), so

Vollständiges README lesen

Computer Use MCP Fragen

Wie füge ich Computer Use MCP zu Claude Code hinzu?

Führe claude mcp add computer-use -- npx -y munim-computer-use in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.

Wie füge ich Computer Use MCP zu Cursor hinzu?

Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.

Welche Tools bietet Computer Use MCP?

Er stellt 2 Tools bereit, darunter wait_timeout_ms, readiness.

Wird der Agent meine Maus bewegen, während er arbeitet?

Nein, er führt Hintergrund-Inputs aus, sodass deine Maus unter deiner Kontrolle bleibt.

Wie erteile ich Berechtigungen auf macOS?

Du musst den Befehl 'munim-computer-use request-permissions' ausführen, um zur Erteilung von Accessibility- und Screen Recording-Berechtigungen aufgefordert zu werden.

Fakten

14. Nov. 2026

Stars: 38
Downloads, 30 Tage: —
Neueste Version: 0.1.0
Letzter Commit: 8. Nov. 2026
Lizenz: Apache-2.0
Transport: stdio
Paket: munim-computer-use

munimtechnologies ↗

Community Publisher

Veröffentlicht von einem unabhängigen Maintainer.

Mehr von munimtechnologies →

Repository verlinkt
Open-Source-Lizenz
Aktiv in den letzten 365 Tagen

Alternativen

Skills für Computer Use

Funktioniert mit

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge für dein README

Zeige deinen HostedMCP-Checks-Score. Das Badge führt Leser zu Installationsanleitungen für jeden Client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/munimtechnologies/computer-use.svg)](https://hostedmcp.org/servers/munimtechnologies/computer-use/checks)

Maintainer?

Übernimm diesen Eintrag, um ihn zu bearbeiten und das HostedMCP-Badge zu deinem README hinzuzufügen.

Eintrag übernehmen

Vor der Installation

Server laufen mit den Berechtigungen, die du ihnen gibst. Nutze den am engsten gefassten Token oder die Datenbank-Role, die für die Aufgabe nötig ist.

Computer Use MCP server

Was ist Computer Use MCP?

Über Computer Use MCP server

Was du damit machen kannst

So installierst du Computer Use MCP

Computer Use MCP tools 2

Konfiguration

Automatisierte Checks

README

Introduction

Table of contents

Quick start

Capability matrix

Computer Use MCP Fragen

Computer Use MCP server

Was ist Computer Use MCP?

Über Computer Use MCP server

Was du damit machen kannst

So installierst du Computer Use MCP

Computer Use MCP tools 2

Konfiguration

Automatisierte Checks

README

Introduction

Table of contents

Quick start

Capability matrix

Computer Use MCP Fragen

Computer Use MCP server

Was ist Computer Use MCP?

Über Computer Use MCP server

Was du damit machen kannst

So installierst du Computer Use MCP

Computer Use MCP in Claude Code installieren

Computer Use MCP in Cursor installieren

Computer Use MCP in VS Code installieren

Computer Use MCP in VS Code CLI installieren

Computer Use MCP in Claude Desktop installieren

Computer Use MCP in Codex installieren

Computer Use MCP in Codex config.toml installieren

Computer Use MCP in Gemini CLI installieren

Computer Use MCP in Gemini settings.json installieren

Computer Use MCP tools 2

Konfiguration

Automatisierte Checks

README

Introduction

Table of contents

Quick start

Capability matrix

Computer Use MCP Fragen

Computer Use MCP server

Was ist Computer Use MCP?

Über Computer Use MCP server

Was du damit machen kannst

So installierst du Computer Use MCP

Computer Use MCP in Claude Code installieren

Computer Use MCP in Cursor installieren

Computer Use MCP in VS Code installieren

Computer Use MCP in VS Code CLI installieren

Computer Use MCP in Claude Desktop installieren

Computer Use MCP in Codex installieren

Computer Use MCP in Codex config.toml installieren

Computer Use MCP in Gemini CLI installieren

Computer Use MCP in Gemini settings.json installieren

Computer Use MCP tools 2

Konfiguration

Automatisierte Checks

README

Introduction

Table of contents

Quick start

Capability matrix

Computer Use MCP Fragen