Permite que los agentes de IA controlen tu escritorio leyendo árboles de accesibilidad y realizando entradas en segundo plano en macOS, Windows y Linux.
También conocido como munimtechnologies/computer-use, computer-use, munim-computer-use
- Stars
- 38
- Herramientas
- 2
- Descargas, 30 días
- —
- Última versión
- 0.1.0
- Último commit
- 8 nov 2026
- Licencia
- Apache-2.0
¿Qué es Computer Use MCP?
Computer Use es un MCP server. Permite que los agentes de IA controlen tu escritorio leyendo árboles de accesibilidad y realizando entradas en segundo plano en macOS, Windows y Linux. Expone 2 herramientas, como wait_timeout_ms, readiness.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Computer Use
Los desarrolladores pueden otorgar a los agentes de IA el control directo sobre sus entornos de escritorio utilizando este MCP server. Funciona como un backend de agente de uso de computadora que permite a los agentes de programación interactuar con sistemas macOS, Windows y Linux tal como lo haría un humano. Al leer los árboles de accesibilidad para identificar IDs de elementos específicos, el servidor permite que los agentes hagan clic y escriban sin necesidad de un modelo de visión para cada interacción.
Una característica destacada es la capacidad de realizar entradas en segundo plano, lo que significa que el agente puede operar de forma invisible para que tu ratón y teclado físicos sigan disponibles para tu propio uso. El servidor funciona con varios clientes MCP, incluyendo Claude Code, Codex, Cursor y MT Code. La configuración consiste en descargar el binario específico para tu plataforma y registrarlo con el agente elegido mediante la línea de comandos o archivos de configuración. Proporciona herramientas para obtener estados de aplicaciones, actuar mediante ID de elemento y verificar acciones a través de capturas de pantalla.
Qué puedes hacer con él
- 1Automatizar flujos de trabajo entre aplicacionesUn agente de IA puede abrir un navegador web para buscar información específica y luego transferir esos datos a una aplicación de notas local.
- 2Realizar tareas de escritorio en segundo planoPuedes tener un agente ejecutando tareas en tu computadora mientras tú sigues usando el ratón y el teclado para otras labores.
- 3Interacción precisa con la UI mediante IDs de elementosEn lugar de adivinar coordenadas de píxeles, un agente puede interactuar con botones y controles específicos utilizando datos de accesibilidad.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Computer Use MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar Computer Use MCP en Claude Code
$ claude mcp add computer-use -- npx -y munim-computer-useInstalar Computer Use MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instalar Computer Use MCP en VS Code
.vscode/mcp.json
{
"servers": {
"computer-use": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instalar Computer Use MCP en VS Code CLI
$ code --add-mcp '{"name":"computer-use","type":"stdio","command":"npx","args":["-y","munim-computer-use"]}'Instalar Computer Use MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Instalar Computer Use MCP en Codex
$ codex mcp add computer-use -- npx -y munim-computer-useInstalar Computer Use MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.computer-use] command = "npx" args = ["-y", "munim-computer-use"]
Instalar Computer Use MCP en Gemini CLI
$ gemini mcp add -s user computer-use npx -- -y munim-computer-useInstalar Computer Use MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"computer-use": {
"command": "npx",
"args": [
"-y",
"munim-computer-use"
]
}
}
}Herramientas de Computer Use MCP 2
Detectado desde el READMEwait_timeout_msreadiness
| wait_timeout_ms | — | |
| readiness | — |
Configuración
COMPUTER_USE_AGENT_CURSORSet to 0 to disable the agent pointer overlay
COMPUTER_USE_BROWSERSet to 0 to hide the browser_* tools
| Nombre | Descripción | Tipo |
|---|---|---|
| COMPUTER_USE_AGENT_CURSOR | Set to 0 to disable the agent pointer overlay | |
| COMPUTER_USE_BROWSER | Set to 0 to hide the browser_* tools |
Verificaciones automáticas
Ejecutado 12 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleAprobado
- Licencia de código abierto (OSI)Aprobado
- Commit o lanzamiento en el último añoAprobado
- El nombre del paquete no es similar a un paquete popularAprobado
- El endpoint remoto usa HTTPSNo verificado
- Las herramientas destructivas están etiquetadasAprobado
- Sin instrucciones ocultas para el modeloAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasAprobado
README
Ver en 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
Preguntas sobre Computer Use MCP
¿Cómo agrego Computer Use MCP a Claude Code?
Ejecuta claude mcp add computer-use -- npx -y munim-computer-use en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Computer Use MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué herramientas proporciona Computer Use MCP?
Expone 2 herramientas, incluidas wait_timeout_ms, readiness.
¿El agente moverá mi ratón mientras trabaja?
No, realiza entradas en segundo plano para que el ratón siga bajo tu control.
¿Cómo otorgo los permisos en macOS?
Debes ejecutar el comando 'munim-computer-use request-permissions' para que se te soliciten los permisos de Accesibilidad y Grabación de pantalla.