Permettez à vos agents IA de contrôler votre bureau en lisant les arbres d'accessibilité et en effectuant des entrées en arrière-plan sur macOS, Windows et Linux.
Aussi connu sous munimtechnologies/computer-use, computer-use, munim-computer-use
- Étoiles
- 38
- Outils
- 2
- Téléchargements, 30 jours
- —
- Dernière version
- 0.1.0
- Dernier commit
- 8 nov. 2026
- Licence
- Apache-2.0
Qu'est-ce que Computer Use MCP ?
Computer Use est un serveur MCP. Permettez à vos agents IA de contrôler votre bureau en lisant les arbres d'accessibilité et en effectuant des entrées en arrière-plan sur macOS, Windows et Linux. Il expose 2 outils, comme wait_timeout_ms, readiness.
Résumé généré à partir du README du projet
À propos du MCP server Computer Use
Les développeurs peuvent donner aux agents IA un contrôle direct sur leur environnement de bureau grâce à ce MCP server. Il fonctionne comme un backend d'agent de type computer-use qui permet aux agents de codage d'interagir avec les systèmes macOS, Windows et Linux comme le ferait un humain. En lisant les arbres d'accessibilité pour identifier des IDs d'éléments spécifiques, le serveur permet aux agents de cliquer et de taper sans nécessiter de modèle de vision pour chaque interaction.
Une fonctionnalité majeure est la capacité d'effectuer des entrées en arrière-plan, ce qui signifie que l'agent peut fonctionner en tâche de fond afin que votre souris et votre clavier physiques restent disponibles pour votre propre usage. Le serveur est compatible avec divers clients MCP, notamment Claude Code, Codex, Cursor et MT Code. L'installation consiste à télécharger le binaire spécifique à votre plateforme et à l'enregistrer auprès de l'agent choisi via la ligne de commande ou des fichiers de configuration. Il fournit des outils pour obtenir l'état des applications, agir par ID d'élément et vérifier les actions via des captures d'écran.
Ce que vous pouvez faire avec
- 1Automatiser des flux de travail multi-applicationsUn agent IA peut ouvrir un navigateur web pour trouver des informations spécifiques, puis transférer ces données dans une application de prise de notes locale.
- 2Exécuter des tâches de bureau en arrière-planVous pouvez laisser un agent exécuter des tâches sur votre ordinateur pendant que vous continuez à utiliser votre souris et votre clavier pour d'autres travaux.
- 3Interaction UI précise via les IDs d'élémentsAu lieu de deviner les coordonnées de pixels, un agent peut interagir avec des boutons et des contrôles spécifiques en utilisant les données d'accessibilité.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer Computer Use MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller Computer Use MCP dans Claude Code
$ claude mcp add computer-use -- npx -y munim-computer-useInstaller Computer Use MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Installer Computer Use MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"computer-use": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Installer Computer Use MCP dans VS Code CLI
$ code --add-mcp '{"name":"computer-use","type":"stdio","command":"npx","args":["-y","munim-computer-use"]}'Installer Computer Use MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Installer Computer Use MCP dans Codex
$ codex mcp add computer-use -- npx -y munim-computer-useInstaller Computer Use MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.computer-use] command = "npx" args = ["-y", "munim-computer-use"]
Installer Computer Use MCP dans Gemini CLI
$ gemini mcp add -s user computer-use npx -- -y munim-computer-useInstaller Computer Use MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Outils MCP Computer Use 2
Détectés depuis le READMEwait_timeout_msreadiness
| wait_timeout_ms | — | |
| readiness | — |
Configuration
COMPUTER_USE_AGENT_CURSORSet to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSERSet to 0 to hide the browser_* tools
| Nom | Description | Type |
|---|---|---|
| COMPUTER_USE_AGENT_CURSOR | Set to 0 to disable the agent pointer overlay | |
| COMPUTER_USE_BROWSER | Set to 0 to hide the browser_* tools |
Vérifications automatisées
Exécuté le 12 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleRéussi
- Licence open source (OSI)Réussi
- Commit ou version publiée au cours de l'année écouléeRéussi
- Nom du package non proche d'un package populaireRéussi
- L'endpoint distant utilise HTTPSNon vérifié
- Les outils destructifs sont étiquetésRéussi
- Aucune instruction cachée destinée au modèleRéussi
- Aucun avis critique dans le package ou ses dépendancesRéussi
README
Voir sur GitHubIntroduction
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.
Table of contents
- 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-permissionsonce 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
Questions sur Computer Use MCP
Comment ajouter Computer Use MCP à Claude Code ?
Exécutez claude mcp add computer-use -- npx -y munim-computer-use dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter Computer Use MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Quels outils Computer Use MCP fournit-il ?
Il expose 2 outils, dont wait_timeout_ms, readiness.
L'agent va-t-il déplacer ma souris pendant son fonctionnement ?
Non, il effectue des entrées en arrière-plan, votre souris reste donc sous votre contrôle.
Comment accorder les permissions sur macOS ?
Vous devez exécuter la commande 'munim-computer-use request-permissions' pour être invité à accorder les permissions d'Accessibilité et d'Enregistrement de l'écran.