Clara Windows UI MCP
Clara Windows UI MCP
面向游戏窗口、旧版桌面应用以及无法通过 UI Automation 可靠暴露的界面等难点目标,提供仅限本地使用的 Windows UI 自动化 MCP 服务器。
为什么存在
内置的 computer-use 流程很方便,但在处理由游戏引擎或自定义图形管线渲染的窗口时,它可能会力不从心。这个 MCP 走的是更底层的路径:
通过
HWND列举并聚焦窗口通过原生 Win32 API 驱动鼠标和键盘输入
将桌面或目标窗口捕获为 PNG 文件
通过 MCP stdio 和小型本地 HTTP API 暴露相同能力
Related MCP server: OmniFlow
当前工具集
list_windowsget_foreground_windowfocus_windowcapture_screenmove_mouseclick_mousepress_keytype_text
视觉基础
src/domain/vision 模块定义了面向调用方的共享视觉契约:
SceneObservation携带捕获来源、OCR 和检测结果。SceneEvent为可选的时序变化通知预留空间。VisionProfileRegistry按applicationId隔离样本、训练集引用与规则。
捕获与检测的实现有意不属于该基础的一部分。调用方应依赖于场景/事件契约,而非检测器的内部实现。
视觉服务与托盘
原生项目与 Clara Cursor 使用相同的安全会话边界:
ClaraVisionBroker Windows service -> local named pipe -> ClaraVisionTray user-session agent代理持久化高层观察状态(
paused或observing)并在本地转发。托盘显示该状态,并让用户启动或暂停观察。
两个组件都不会捕获桌面,也不会执行自动化。只有在定义目标选择和捕获策略之后,未来的会话 agent 才会接入现有的 opt-in 捕获管线。
以 Release 配置构建 native/ClaraVisionBroker 和 native/ClaraVisionTray,然后在提升的 Command Prompt 中运行 scripts/install-vision-service.cmd,在交互式用户会话中运行 scripts/install-vision-tray.cmd。
运行
npm.cmd install
npm.cmd run build
npm.cmd run start:stdio本地诊断:
npm.cmd run start:api架构选择
运行模式:
stdio、api或both部署形态:仅本地
认证:无
存储:仅将捕获输出为本地文件
组织:CQRS 风格的命令与查询,配传输适配器
说明
截图写入
captures/下。此首版刻意避开 UIA,以便对游戏和性能画布的应用仍然有用。
下一个逻辑方向是目标感知匹配,基于模板图像、像素区域或 OCR。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables comprehensive Windows desktop automation including screen capture, OCR text extraction, mouse/keyboard control, window management, process control, and clipboard operations through 25+ tools for AI agents.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to automate Windows desktop applications through window manipulation, image recognition, OCR, keyboard/mouse simulation, and memory operations via the MCP protocol.MIT
- FlicenseNot gradedqualityDmaintenanceEnables automation of native Windows desktop applications through screen capture, mouse/keyboard control, and waiting for UI changes, exposing them as MCP tools.1
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to control Windows GUI applications like a human using screen capture, OCR, mouse and keyboard input, and window management, with safety levels and memory.
Related MCP Connectors
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Automate cloud browsers to navigate websites, interact with elements, and extract structured data.…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BestCodeTools/clara-windows-ui-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server