Biarkan AI agent mengontrol desktop Anda dengan membaca accessibility trees dan melakukan input di background pada macOS, Windows, dan Linux.
Juga dikenal sebagai munimtechnologies/computer-use, computer-use, munim-computer-use
- Stars
- 38
- Tools
- 2
- Unduhan, 30 hari
- —
- Versi terbaru
- 0.1.0
- Commit terakhir
- 8 Nov 2026
- Lisensi
- Apache-2.0
Apa itu Computer Use MCP?
Computer Use adalah MCP server. Biarkan AI agent mengontrol desktop Anda dengan membaca accessibility trees dan melakukan input di background pada macOS, Windows, dan Linux. Server ini menyediakan 2 tool, seperti wait_timeout_ms, readiness.
Ringkasan dibuat dari README proyek
Tentang Computer Use MCP server
Developer dapat memberikan kontrol langsung kepada AI agent atas lingkungan desktop mereka menggunakan MCP server ini. Server ini berfungsi sebagai backend computer-use agent yang memungkinkan coding agent berinteraksi dengan sistem macOS, Windows, dan Linux layaknya manusia. Dengan membaca accessibility trees untuk mengidentifikasi element ID tertentu, server ini memungkinkan agent untuk melakukan klik dan mengetik tanpa memerlukan vision model untuk setiap interaksi.
Fitur unggulannya adalah kemampuan untuk melakukan background input, yang berarti agent dapat beroperasi di latar belakang sehingga mouse dan keyboard fisik Anda tetap tersedia untuk digunakan sendiri. Server ini bekerja dengan berbagai MCP client termasuk Claude Code, Codex, Cursor, dan MT Code. Setup melibatkan pengunduhan binary spesifik platform dan mendaftarkannya ke agent pilihan Anda melalui command line atau file konfigurasi. Server ini menyediakan tools untuk mendapatkan app state, bertindak berdasarkan element ID, dan memverifikasi tindakan melalui screenshot.
Apa yang bisa Anda lakukan dengannya
- 1Automate cross-application workflowsAI agent dapat membuka web browser untuk mencari informasi spesifik dan kemudian memindahkan data tersebut ke aplikasi pencatat lokal.
- 2Perform background desktop tasksAnda dapat menjalankan agent untuk mengerjakan tugas di komputer Anda sementara Anda tetap menggunakan mouse dan keyboard untuk pekerjaan lain.
- 3Precise UI interaction via element IDsAlih-alih menebak koordinat pixel, agent dapat berinteraksi dengan tombol dan kontrol spesifik menggunakan data accessibility.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal Computer Use MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal Computer Use MCP di Claude Code
$ claude mcp add computer-use -- npx -y munim-computer-useInstal Computer Use MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instal Computer Use MCP di VS Code
.vscode/mcp.json
{
"servers": {
"computer-use": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instal Computer Use MCP di VS Code CLI
$ code --add-mcp '{"name":"computer-use","type":"stdio","command":"npx","args":["-y","munim-computer-use"]}'Instal Computer Use MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instal Computer Use MCP di Codex
$ codex mcp add computer-use -- npx -y munim-computer-useInstal Computer Use MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.computer-use] command = "npx" args = ["-y", "munim-computer-use"]
Instal Computer Use MCP di Gemini CLI
$ gemini mcp add -s user computer-use npx -- -y munim-computer-useInstal Computer Use MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Tool Computer Use MCP 2
Terdeteksi dari READMEwait_timeout_msreadiness
| wait_timeout_ms | — | |
| readiness | — |
Konfigurasi
COMPUTER_USE_AGENT_CURSORSet to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSERSet to 0 to hide the browser_* tools
| Nama | Deskripsi | Tipe |
|---|---|---|
| COMPUTER_USE_AGENT_CURSOR | Set to 0 to disable the agent pointer overlay | |
| COMPUTER_USE_BROWSER | Set to 0 to hide the browser_* tools |
Pengecekan otomatis
Berjalan 12 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkauLolos
- Lisensi open source (OSI)Lolos
- Ada commit atau release dalam satu tahun terakhirLolos
- Nama package tidak mirip dengan package populerLolos
- Remote endpoint menggunakan HTTPSTidak diperiksa
- Tools yang bersifat destruktif telah diberi labelLolos
- Tidak ada instruksi tersembunyi untuk modelLolos
- Tidak ada advisory kritis pada paket atau dependensinyaLolos
README
Lihat di 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
Pertanyaan tentang Computer Use MCP
Bagaimana cara menambahkan Computer Use MCP ke Claude Code?
Jalankan claude mcp add computer-use -- npx -y munim-computer-use di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan Computer Use MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Tool apa yang disediakan Computer Use MCP?
Server ini menyediakan 2 tool, termasuk wait_timeout_ms, readiness.
Apakah agent akan menggerakkan mouse saya saat sedang bekerja?
Tidak, agent melakukan input di background sehingga mouse Anda tetap berada di bawah kendali Anda.
Bagaimana cara memberikan izin di macOS?
Anda harus menjalankan command 'munim-computer-use request-permissions' untuk memunculkan prompt izin Accessibility dan Screen Recording.