Permite que un agente de IA lea el escritorio como un mapa de interfaz de usuario para hacer clic, escribir y actuar sobre elementos por su nombre, verificando cada acción.
También conocido como AmrDab/clawdcursor
- Stars
- 407
- Herramientas
- —
- Descargas, 30 días
- 3358
- Última versión
- 2.0.0
- Último commit
- 14 nov 2026
- Licencia
- MIT
¿Qué es Clawd Cursor MCP?
Permite que un agente de IA lea el escritorio como un mapa de interfaz de usuario para hacer clic, escribir y actuar sobre elementos por su nombre, verificando cada acción.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Clawd Cursor
Los desarrolladores que necesitan que agentes de IA interactúen con aplicaciones de escritorio y navegadores web pueden usar Clawd Cursor para convertir una computadora en un mapa de UI navegable. En lugar de depender únicamente de coordenadas visuales, el servidor permite que un cliente de IA identifique y actúe sobre elementos de la interfaz por su nombre, como botones o campos de texto. Funciona en Windows, macOS y Linux priorizando el método más eficiente disponible, comenzando con la página del navegador o el árbol de accesibilidad que utilizan los lectores de pantalla, y recurriendo después al reconocimiento de texto y capturas de pantalla.
Los usuarios conectan su cliente MCP preferido, como Claude o Cursor, al servidor para acceder a herramientas como accessibility, system, window, browser, computer y batch. El servidor no proporciona su propio modelo ni requiere una clave de API, ya que el cliente de IA toma todas las decisiones. Después de cada acción, el servidor informa si el cambio fue confirmado, no verificado o fallido, asegurando que el agente pueda verificar su progreso. Esta configuración ofrece una forma de que los agentes realicen tareas que solo existen dentro de una interfaz gráfica de usuario.
Qué puedes hacer con él
- 1Automatizar flujos de trabajo de aplicaciones de escritorioDirige a un agente de IA para hacer clic en botones específicos y completar formularios en software nativo de escritorio usando nombres de elementos.
- 2Controlar navegadores web vía PlaywrightPermite que una IA navegue por sitios web e interactúe con elementos de la página a través de una ventana de navegador dedicada.
- 3Interactuar con elementos de UI no estándarUsa el reconocimiento de texto para encontrar y hacer clic en etiquetas cuando una aplicación no proporciona un árbol de accesibilidad.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Clawd Cursor MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar Clawd Cursor MCP en Claude Code
$ claude mcp add clawdcursor -- npx -y clawdcursorInstalar Clawd Cursor MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"clawdcursor": {
"command": "npx",
"args": [
"-y",
"clawdcursor"
]
}
}
}Instalar Clawd Cursor MCP en VS Code
.vscode/mcp.json
{
"servers": {
"clawdcursor": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"clawdcursor"
]
}
}
}Instalar Clawd Cursor MCP en VS Code CLI
$ code --add-mcp '{"name":"clawdcursor","type":"stdio","command":"npx","args":["-y","clawdcursor"]}'Instalar Clawd Cursor MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"clawdcursor": {
"command": "npx",
"args": [
"-y",
"clawdcursor"
]
}
}
}Instalar Clawd Cursor MCP en Codex
$ codex mcp add clawdcursor -- npx -y clawdcursorInstalar Clawd Cursor MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.clawdcursor] command = "npx" args = ["-y", "clawdcursor"]
Instalar Clawd Cursor MCP en Gemini CLI
$ gemini mcp add -s user clawdcursor npx -- -y clawdcursorInstalar Clawd Cursor MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"clawdcursor": {
"command": "npx",
"args": [
"-y",
"clawdcursor"
]
}
}
}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 etiquetadasNo verificado
- Sin instrucciones ocultas para el modeloAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasAprobado
README
Ver en GitHubWhat's new
2.0.0 — A tool, driven by your agent. (First published as 1.6.0; renumbered because it is a breaking change.) (full changelog)
- Breaking: the built-in agent loop and all model settings are gone. Claude, Codex, Cursor, a local Llama or any MCP client drives the six tools (
accessibility,system,window,browser,computer,batch); thetasktool and the--provider/--model/--api-keyflags are removed. - Breaking: the policy gate is gone, so
open_file, closing a window, clipboard writes and clicking "Send" by name work. What still protects you: Stop, the pause card, no stray input into AI assistant windows, a short per-OS list of session-ending keys, and your MCP host's own approval prompts. If your host auto-approves tool calls, nothing asks before an irreversible action: see SECURITY.md (an opt-in confirm mode is coming in 2.1). - A thin outline around the window the agent is working in replaces the full-screen glow; the pill sits on that window's monitor.
- Results you can trust: a value is "set" only when the field shows it;
copy_all_textnever presses keys outside a browser;open_appnever names another app's window; actions by name never press a hidden element. - Keys follow the OS: the agent is told its modifier (
cmdorctrl) up front, and shortcuts are offered only for this OS. - Second monitors above or left of the main one, Retina zoom areas, and slow-starting apps now work as expected.
1.5.27 — Results you can trust, and logs that say what happened.
- Ticks, dropdowns and expanders read and change the same way on Windows, macOS and Linux;
togglereports the state it actually reached, and actions by name aim at the control, not its label. - A stop always answers "stopped by the user" first, and also blocks hover, clipboard writes, page script and tab switches.
- Typing goes only to the window the agent was working in, dialogs like Save As included.
- Linux reads deep web pages, and a search that runs out of time or elements says so instead of "not found".
- Logs in
~/.clawdcursor/logs/show every call's timing and outcome, slow internal steps, why the server exited, and who stopped it, with no typed text, error text or window titles.
1.5.26 — The agent asks you on screen, and the pill says what it is doing.
- Security (Windows, high): text the agent typed or copied could run as PowerShell code (GHSA-9ppf-38v8-h97v). Fixed; upgrade.
- The pause prompt is a card: the agent can offer 2-6 choices to click, or a text box, and gets your exact answer back. A choice is never a safety approval.
- A redesigned pill: what the agent is doing right now ("Typing in Edge"), how long it has been running, and a Stop button.
- A field below the fold is scrolled into view instead of refused (verified on Windows; the macOS and Linux calls are in but not yet run on a real desktop).
- macOS: when a password field holds secure input,
window focusnames the app holding it instead of failing vaguely.
1.5.25 — A stop really stops, and keys only go to the window the agent was working in.
- Double-click the pill and every clawdcursor process stops: a running wait ends at once, the rest of a batch never runs, and it stays stopped (even across restarts) until you click Resume.
- Every key, paste and click first checks that the agent's window is still in front. If you switched apps, nothing is sent and the agent is told so.
- Safety gate: key combos are blocked however their modifiers are spelled,
shortcuts_executeand compound actions are gated like the tools they run, and every element an invoke may act on is checked. --no-visionnow really keeps screenshots from every model; the daemon is loopback-only (use an SSH tunnel for remote), andserver.portin config works.- macOS: the Screen Recording check works without the helper built, and
doctorasks the same question screenshots do.
1.5.24 — The AI never touches your pill, and failures stop looking like results.
- While a pause waits for you, nothing reads, clicks or types. The pill and pause prompt are never a target, even from another clawdcursor process.
- On macOS, a screenshot without Screen Recording permission is an error, not a wallpaper image, and open popovers are readable.
- The browser clawdcursor drives comes to the front when it navigates.
- A failed OCR read reports its error instead of "No text detected", and OCR
confidenceis only shown when the engine really has one.
1.5.23 — Windows: finding an element by name no longer matches stray letters. A lone "C" on another page could match "User code 0", and "Don't Save" could match Save. A partial match now has to be a real part of the name you asked for.
1.5.22 — Your turn is as short as possible. When an agent needs you (a sign-in, a 2FA code), it asks for that one step and does the rest itself. With done_when (what shows on screen once you're done), the prompt turns from blue back to amber the moment you finish, with no Resume click.
1.5.21
set_valuenever guesses a field. With no field name or role it used to type into the window's largest text box; it now asks you to name the field.- macOS: no screen-recording permission no longer breaks everything. Only screenshots and OCR fail, and they say how to fix it; windows, keys and accessibility keep working.
- Cleaner page text on Windows (no placeholder characters), and a security update to a dependency.
1.5.20
- The on-screen pill no longer blocks the agent's own clicks. It sits where browsers keep their tabs and address bar; it now steps aside for a moment before every click, drag or scroll, then comes back. Windows, macOS and Linux.
- Reading a page no longer highlights it on Linux and macOS either.
copy_all_textreads the document through accessibility, as on Windows: exact text, nothing selected, your clipboard untouched. - Your clipboard is put back after typing (
smart_typetoo), and only once the paste has landed, so a slow app can't paste what you had copied. - macOS:
window focusfocuses the process you asked for, a locked screen says so, sidebar clicks are verified, and a bare modifier key (shift) works.
1.5.19 — Typing never pastes your own clipboard. clawdcursor types by pasting; on Windows a clipboard write could fail silently and the paste then sent whatever you had copied. Every paste now checks the clipboard first and types key by key when it doesn't hold the text.
1.5.18
- "Something else" on the pause prompt. When the agent pauses for you, the prompt has a third button between Resume and End task: type an answer instead of doing the step — "use the test account instead", a code, a change of plan — and press Enter. The agent continues from what you wrote. Windows, macOS and Linux; over MCP
pause_for_userreturns{status:"replied", reply}. - Reading a page no longer highlights it (Windows).
copy_all_textreads the document the way a screen reader does: exact text, no Ctrl+A, nothing selected, your clipboard untouched. - MCP tool annotations on every tool, and
window/systemnow describe every action, its side effects and what it returns.
1.5.17
- macOS: text outside ASCII is typed and pasted as itself — "café 日本語" no longer comes out as "cafa aaa" or "caf√©".
copy_all_textnever selects an editor or a list (Ctrl+A there selected a whole document or every email).
1.5.16
- It pauses for you at a roadblock, then carries on. A sign-in, a 2FA code, a CAPTCHA, an upgrade page: instead of giving up, the agent pauses. The glow around the screen turns blue and an on-screen prompt says what it needs ("Sign in to Outlook, then click Resume"). Click Resume and it continues where it left off, or End task to stop. Your own agent can do the same over MCP with
system({ action: "pause_for_user", message }); from a terminal,clawdcursor resume(or--end). - The glow and banner on every OS. macOS and Linux now get the same screen-edge glow and banner as Windows: amber while the agent works, blue while it waits for you. Double-click the banner to stop everything.
- Blind mode on macOS caught up with Windows. A native accessibility helper lists windows in 0.3 s (was 11 s) and reads a window's tree in 0.06–0.2 s. Typing is refused while a system dialog owns the keyboard, and the agent is told when another app's dialog took its keys.
- Sharper blind mode on Windows and Linux. Classic controls no longer read as blank panes, the open dialog is what gets read, no 10 s stall on buttons that open a modal, the right field is found by name, and focusing a window no longer un-maximizes it.
- Upgrade walls are a roadblock. The agent is told to stop at
Upgrade,SubscribeorStart trialand ask you on the pause prompt. - Know what you're running.
clawdcursor versionslists every installed copy (global npm, Claude Desktop extension, Claude Code plugin), and the installers say what they updated.
Everything else is in the changelog.
What it is
Clawd Cursor is a local MCP server that gives any tool-calling agent — Claude Code, Cursor, Windsurf, OpenClaw, the Claude Agent SDK, or your own loop — safe control of the real desktop. It clicks, types, reads the screen, opens apps, and drives any GUI the way a human would: native apps, the browser, even a canvas.
Most "let an agent use the computer" tools take a screenshot and feed it to a vision model — slow, expensive, and brittle. Clawd Cursor compiles the screen into one UI map: it fuses the accessibility tree and OCR into a confidence-scored set of elements, each tagged with a stable el_NN id, and acts on elements by id — not pixel coordinates. Coordinates appear only in the last-resort screenshot/vision tier (live pixels off the current frame), for canvas-only apps or tasks that genuinely need spatial reasoning. The result is cheaper, faster, private, and — uniquely — it checks that each action actually did what it claimed.
If a human can do it on a screen, your agent can too. No API, no integration, no problem — only the right sequence of reads, clicks, keys, and waits. Use it as the last-mile fallback: native API exists? Use it. CLI? Use it. Clawd Cursor is for the click, the legacy app, the GUI with no public surface.
Why it's different
The desktop-agent space is crowded. The closest install-and-go peers are Windows-MCP and Terminator (desktop MCP servers); browser-only tools (browser-use, Playwright MCP) are adjacent; and OmniParser / UI-TARS are vision-centric parsing approaches you'd build an agent around, not products you install. Here's the honest comparison across those approaches — what Clawd Cursor does that the popular options don't:
| Clawd Cursor | browser-use | Playwright MCP | OmniParser / UI-TARS | computer-use | |
|---|---|---|---|---|---|
| Any desktop app, not just the web | ✅ | web only | web only | ✅ | ✅ |
| Cross-OS (Windows + macOS + Linux) | ✅ | — | — | varies | sandbox |
| Perception without a vision model | ✅ compiled a11y + OCR map | DOM | a11y tree | ❌ vision-centric | ❌ vision |
| Verifies its own actions (deviation) | ✅ | — | — | — | — |
| A Stop that holds (every process, across restarts) | ✅ | — | — | — | — |
| Any model / vendor | ✅ | ✅ | not an agent | model-specific | Claude only |
| MCP-native (one config, any host) | ✅ | library | test framework | — | tool-use API |
| Local-only, no cloud required | ✅ | ✅ | ✅ | needs a model | screens → cloud |
Three things here are genuinely rare:
- Cheapest-tier-first perception, fully local. Accessibility tree (free) → OCR (cheap) → screenshot (expensive — the only tier that puts pixels in the model's context; "screenshot" and "vision" are the same step). The agent climbs only when it must, so token cost tracks task difficulty — and with a local model, nothing leaves the machine. Vision-centric agents (OmniParser, UI-TARS) need a screenshot in the model for every observation.
- It verifies. Pass
expecton a consequential action and Clawd Cursor re-checks the live screen (with a short settle window for async UIs) and reports a DEVIATION instead of a hollow "success." A completed task can't be marked done on evidence that was already true before it acted. - You stay in control, and the roles are clear. clawdcursor is a tool layer that runs with your own permissions: what to do is decided by your agent and by your MCP host's permission prompts, which clawdcursor feeds with accurate read-only / destructive tool annotations. What clawdcursor guarantees itself is small and holds for every call: a Stop that every process honours, a pause only you can answer, no stray input into the AI assistant's own window, and a short list of key combos (lock, log out) it never sends. See SECURITY.md.
Plus: whenever an agent is driving, an on-screen banner that says what it is doing ("Typing in Edge") and a thin amber outline around the window it is working in (nothing over the window, nothing on the rest of the screen), on Windows, macOS and Linux — press Stop on the banner to stop. A stop holds until you give control back: the agent's next request comes up as a prompt, and only your Resume lets it act again (or run clawdcursor resume). Keys and clicks also go only to the window the agent was working in: if you switch apps while it waits, its next input is refused instead of landing in your window. When the agent needs you (a sign-in, a 2FA code), the outline turns blue and the banner says what to do, with Resume and End task. A human at the machine always knows, and always has a kill switch.
Install
clawdcursor is an MCP server published to npm — install it into any MCP-capable agent (Claude Code, Claude Desktop, Cursor, Windsurf, Zed, OpenAI Codex, or your own loop) the same way you install any other MCP server.
Claude Desktop — one-click extension (no terminal)
Download the extension for your OS and open it — Claude Desktop installs it:
| Windows | macOS | Linux |
|---|---|---|
| clawdcursor-win32.mcpb | clawdcursor-darwin.mcpb | clawdcursor-linux.mcpb |
- Double-click the file (or Settings → Extensions → Advanced settings → Install Extension… and pick it).
- Turn on Allow clawdcursor to control this computer — that is the one-time desktop-control consent; until it is on, every tool returns a consent prompt.
- macOS: the first time macOS asks, allow Claude under Privacy & Security → Accessibility and Screen Recording.
No Node.js, npm or JSON editing needed — Claude Desktop runs the bundled server itself. Everything below is for other agents, or for Claude Desktop without the extension.
1 — Install the engine + grant consent (once)
npm i -g clawdcursor
clawdcursor consent --accept # one-time desktop-control consent (required)
clawdcursor grant # macOS only — approve Accessibility + Screen Recording
Hosts that support MCP elicitation (e.g. Claude Code, VS Code) also let you skip
consent --accept: the first tool call asks "Allow clawdcursor to control this computer" right in the app.
Zero-install also works — swap
clawdcursorfornpx -y clawdcursorin any snippet below and npx fetches it on demand. A global install is recommended anyway: it's pinnable and inspectable on disk (safer for a tool with full desktop control than auto-fetchinglatestevery run), and it's the path on which the macOS native helper builds at install time. Requires Node.js 20+.
Per-OS prerequisites. Windows installs clean —
sharpand@nut-tree-fork/nut-jsship prebuilt binaries, so no C++/Python build tools are needed. macOS needs Xcode Command Line Tools (xcode-select --install) for screenshots / vision; core accessibility-driven control still works without them. Linux needs a few system packages npm can't install:tesseract-ocr(OCR),python3-gi+gir1.2-atspi-2.0(accessibility tree), and — on Wayland —ydotool(synthetic input).
2 — Add it to your agent (pick your host)
One click (Cursor, VS Code):
Every host runs the same command — clawdcursor mcp --compact, or
npx -y clawdcursor mcp --compact with no global install. Only the config shape
differs between hosts:
Claude Code
claude mcp add clawdcursor -s user -- clawdcursor mcp --compact
Cursor · Windsurf · Claude Desktop · Cline · Gemini CLI — the common mcpServers shape:
{
"mcpServers": {
"clawdcursor": { "command": "clawdcursor", "args": ["mcp", "--compact"] }
}
}
Claude Desktop reads %APPDATA%\Claude\claude_desktop_config.json (Windows) or
~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
Gemini CLI reads ~/.gemini/settings.json.
VS Code (Copilot) — .vscode/mcp.json uses servers, not mcpServers:
{
"servers": {
"clawdcursor": { "command": "clawdcursor", "args": ["mcp", "--compact"] }
}
}
Zed — context_servers in settings.json:
{
"context_servers": {
"clawdcursor": { "command": "clawdcursor", "args": ["mcp", "--compact"] }
}
}
OpenAI Codex — ~/.codex/config.toml. The first launch can take a few seconds,
so raise the 10 s default startup timeout:
[mcp_servers.clawdcursor]
command = "clawdcursor"
args = ["mcp", "--compact"]
startup_timeout_sec = 30
opencode — opencode.json uses mcp, and command is an array:
{
"mcp": {
"clawdcursor": { "type": "local", "command": ["clawdcursor", "mcp", "--compact"] }
}
}
Any other MCP host (Goose, Continue, …) — register a stdio server with command
clawdcursor and args mcp --compact.
Windows: some hosts start the server without a shell, and then can't find
clawdcursorornpx(both are.cmdshims). If the server won't start, wrap it incmd /c— e.g."command": "cmd", "args": ["/c", "clawdcursor", "mcp", "--compact"], orclaude mcp add clawdcursor -s user -- cmd /c clawdcursor mcp --compact.
That's the whole setup. Ask your agent: "open Outlook and reply to the latest email from Sarah."
Or: one-command plugin (Claude Code)
Skip the manual config — this repo ships a plugin that registers the tools and
bundles the usage skill in one step. It resolves the package's bin (never a
hard-coded dist/ path), so an upgrade can't break it:
claude plugin marketplace add AmrDab/clawdcursor
claude plugin install clawdcursor@clawdcursor
# Windows (PowerShell)
powershell -c "irm https://clawdcursor.com/install.ps1 | iex"
Preguntas sobre Clawd Cursor MCP
¿Cómo agrego Clawd Cursor MCP a Claude Code?
Ejecuta claude mcp add clawdcursor -- npx -y clawdcursor en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Clawd Cursor 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.
¿Clawd Cursor lee la pantalla con capturas de pantalla o accesibilidad?
Utiliza primero la estructura de accesibilidad y OCR, y trata las capturas de pantalla y la visión como último recurso.
¿Cómo detengo al agente para que no controle mi escritorio?
Haz doble clic en la píldora en pantalla para detener todos los procesos de clawdcursor; permanecerá detenido hasta que hagas clic en Resume.
¿Clawd Cursor necesita claves de API o una configuración de modelo?
No. Se eliminaron el bucle del agente integrado y los ajustes del modelo, por lo que tu propio cliente MCP como Claude o Cursor es el que dirige las herramientas.
¿Qué pasa cuando el agente se encuentra con un inicio de sesión o un prompt de 2FA?
El agente se pausa, muestra un aviso en pantalla explicando lo que necesita y continúa donde se quedó después de que hagas clic en Resume.