원클릭으로
argus-codex-computer-use
Use Argus from Codex to observe and operate Windows desktop applications through a local MCP server.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use Argus from Codex to observe and operate Windows desktop applications through a local MCP server.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | argus-codex-computer-use |
| description | Use Argus from Codex to observe and operate Windows desktop applications through a local MCP server. |
Use the argus-codex MCP server for Windows desktop automation from Codex.
This server is local-only: it does not call the OpenAI API and does not require
OPENAI_API_KEY.
computer_status to verify the local server is available.computer_open_application for the target app, such as
{"app":"EXCEL.EXE"} or {"app":"c:\\program files\\tencent\\weixin\\weixin.exe"}.computer_observe before coordinate-based actions.computer_execute with action objects.Coordinates default to image-space pixels from the last computer_observe
screenshot. Pass coordinateSpace: "display" only for absolute display
coordinates.
click: { "type": "click", "x": 100, "y": 200 }double_click: { "type": "double_click", "x": 100, "y": 200 }scroll: { "type": "scroll", "x": 100, "y": 200, "dy": 3 }type: { "type": "type", "text": "hello" }keypress: { "type": "keypress", "keys": ["CTRL", "V"] }drag: { "type": "drag", "from": { "x": 100, "y": 200 }, "to": { "x": 300, "y": 200 } }move: { "type": "move", "x": 100, "y": 200 }wait: { "type": "wait", "seconds": 1 }For Chinese text, use the type action. Argus routes non-ASCII text through a
clipboard paste path internally.
Use Argus from Codex on Windows to observe and operate desktop applications through the local MCP server without requiring an OpenAI API key.
Desktop GUI automation via the Argus MCP server. Use when the user asks to control their computer, interact with desktop applications, take screenshots, click UI elements, type text, scroll, manage windows, or automate any GUI task. Triggers: "screenshot", "click on", "open app", "type into", "scroll", "computer use", "GUI automation", "desktop control", "操作电脑", "截屏", "点击", "打开应用", "输入文字".