NexusWindows for Codex

io.github.pironjulien由 GitHub 账号 pironjulien 发布v3.7.4更新于 Nov 3, 2026

Windows computer use in the background for Codex: UI Automation, Win32 messages, read back.

概览

AI 生成的概览

让助手在后台查看并操作 Windows 桌面应用,基于 UI Automation、Win32 消息和可验证的步骤。

可以做什么
  • 列出桌面窗口和打开的对话框,可按标题或应用筛选
  • 在后台查看单个窗口:UI Automation 树或原生截图
  • 用选择器在该窗口上执行步骤,每步带预期结果,遇到未验证的步骤即停止
  • 启动应用、文件夹、文档或系统设置页面,并返回由此产生的窗口
  • 关闭窗口,遇到保存提示时只报告而不代为回答
适用场景
适合让助手在用户继续工作的同时操作 Windows 桌面应用,例如填写表单、读取对话框,或驱动没有 API 的旧式软件。
运行要求
作为本地 stdio 进程在 Windows 上运行,通过 npx 从 npm 包启动;仅限桌面,无网页版。未声明认证、环境变量或请求头。
安装前请注意
它会操作真实的桌面应用,包括输入、点击和关闭窗口,出错会影响用户正在使用的会话。密码管理器不会被列出,但其他窗口可能显示敏感信息。付款、发送、发布或永久删除类操作需用户本人下令确认才会执行。屏幕上读到的文字应视为数据而非指令。

安装

在 SourceWeft 中

  1. 打开 控制台中的 NexusWindows for Codex,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

该仓库没有 README。

工具

5

windows

List windows

Application windows on the desktop (id, app, title, pid), like the taskbar, plus open dialogs (a file "Open" box…) with dialogOf: the window that owns them; look at a dialog by its id or title. Password managers are never listed. filter: part of a title or app.

输入参数filter

look

Look at a window

See a window in the background, without bringing it forward: UI Automation tree (roles, names, ids, values, states) and, with mode image or both, a native capture that works even when the window is covered (WebP, at most 2000 px; unchanged since the last image sent: not attached again, mode image always attaches it). A window with almost no tree (Tk, canvas, game: fewer than 6 elements) also gets the text of its image read by OCR (ocr.lines: text, point, screenshotId), clicked with point + screenshotId. Selects that window for act; an observation serves one act and expires after 60 s. Returns its observation id: pass it to act (required from protocol 2026-07-28).

输入参数modeimagemarksregionwindow

act

Act in the window

Steps on the window of the last look, in the background first (Win32 messages, UI Automation, DevTools for Chromium), the real mouse/keyboard only as a fallback under the shared foreground token. One step, or up to 32 each with its own expect; stops at the first step not verified. Per step: ✓ verified, = already done, ~ unknown (never replayed: look again), ✗ failed or refused. interaction: true keeps the window in front for the whole call (shared foreground token, at most 30 s, given back at the end) for a menu that closes when the foreground goes back (a context menu opened by a real right click, then its command): selectors only, every step with its expect; look again afterwards.

输入参数steps必填interactionobservation

launch

Launch an app, folder or document

Open an application (name, absolute path or Store app id, with its arguments), a folder or a document (absolute path) or a Settings page (ms-settings:...) and give the foreground back to the user. Returns the windows attributed to this launch, each with its proof: "process" (the process the shell returned), "folder" (a new Explorer window showing exactly that folder) or "application" (the requested application, started after the request: another instance started at the same moment could be taken for it; a Store app by its app id); other new windows come back as candidates (outcome unknown). Look at one before acting.

输入参数app必填args

window

Manage a window

close: close the window (one close message, read back; a "save?" prompt is reported, never answered).

输入参数action必填window

版本历史

5
  1. v3.7.4最新Oct 29, 2026
  2. v3.1.7Oct 26, 2026
  3. v3.1.6Oct 26, 2026
  4. v3.1.1Oct 24, 2026
  5. v3.0.1Oct 23, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证10 分