
uMouse MCP
io.github.SonicloudTech由 GitHub 账号 SonicloudTech 发布v0.1.1更新于 Oct 26, 2026
USB HID mouse control and voice dictation for Windows x64. Requires compatible uMouse hardware.
概览
面向 Windows x64 的 MCP 服务器,让 AI 助手通过真实的 uMouse USB HID 鼠标执行移动、点击、滚动、拖拽,并支持语音听写。
- 可以做什么
- 按桌面物理像素坐标移动、点击、滚动和拖拽系统光标,支持多显示器与可选高精度模式
- 开始与结束独占控制任务,同一时间只允许一个任务驱动鼠标和键盘
- 以只读方式读取光标位置、实时按键状态和前台窗口信息
- 在操作前检查 SDK 状态、设备列表和上报的能力
- 采集麦克风音频,经可插拔的语音识别提供方生成预览与最终转写文本
- 适用场景
- 适合需要助手通过真实硬件输入操作 Windows 桌面的场景,例如驱动浏览器或应用界面,或把口述内容输入当前焦点窗口。只有已拥有兼容 uMouse 硬件时才值得安装。
- 运行要求
- 仅支持 Windows x64,需要兼容的 uMouse 硬件与固件(普通 USB 或蓝牙鼠标不可用)。需另行安装 Node.js 22 x64;发布版 ZIP 或 MCPB 包需解压或导入,客户端配置指向解压目录。语音听写需配置语音提供方,MCPB 包默认关闭或使用本地 windows-speech。
安装
在 SourceWeft 中
- 打开 控制台中的 uMouse MCP,将其添加到工作区。
- 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
uMouse MCP — Hardware Mouse Control for AI Agents
English | 简体中文
[release] [MCP Registry] [code license] [platform] [ASR]
Give AI agents a real hardware mouse. uMouse MCP is a Model Context Protocol (MCP) server for USB HID mouse control and voice dictation on Windows. Mouse movement, clicks, scrolling and dragging use a compatible uMouse device; voice input supports pluggable speech recognition providers.
Requires compatible uMouse hardware and firmware, Windows x64, and a separately installed Node.js runtime (use Node.js 22 x64). An ordinary USB mouse is not sufficient. The MIT license covers the server code; native SDK binaries have separate terms. See License.
Download · Quick start · Reference demos · Documentation · Compatibility & FAQ · Get hardware / support · uMouse SDK
Download
All releases · Gitee release mirror
MCPB installation: import the .mcpb into a client that supports MCPB Node extensions. Version 0.1.1 wraps the legacy 0.1.0 runtime, includes no cloud credentials, and defaults speech recognition to disabled; windows-speech is the optional local provider. Data defaults to ~/.umouse-mcp-mcpb. See the bilingual MCPB guide. Published in the official MCP Registry as io.github.SonicloudTech/mouse-mcp; metadata in server.json, publication and validation.
The ZIP includes production Node dependencies, native SDK DLLs, the voice preview UI and VC runtime libraries. No npm install or compilation is required to use the release; Node.js itself is not bundled.
Release and source are different installation paths: the v0.1.0 installer registers the legacy stdio entry, mcp/dist/index.js. The shared-v2 tools, native host and acceptance lab described below belong to the source implementation. This ZIP is not a complete shared-v2 bundle: it does not contain that native host or the acceptance lab. Use the installed server's tool list and the README shipped inside the ZIP for release-specific behavior.
Quick start
The following steps use the original ZIP. For MCPB, use the import instructions above, then perform the status/device checks in step 5.
- Install Node.js 22 x64 and confirm
node --versionworks. Connect a compatible uMouse USB receiver/device and power on the mouse. For a device or firmware compatibility check, see Hardware & support. - Download the ZIP above and extract it. Open the
umouse-mcp-os-win-x64folder; keep it in a permanent location because client configuration points to this folder. - Double-click
install-agents.cmdto register ZCode at user scope, or run one command for your chosen client from the extracted folder:
The installer adds or updates the umouse entry in the selected client's configuration. It also copies the bundled trial ASR configuration into the local data directory if no configuration already exists. Replace trial credentials with your own for production use.
- Open a new ZCode session, fully quit and reopen Claude Desktop, or reload the Cursor window, as appropriate.
- Ask your agent to call
umouse_status,umouse_get_capabilities, andumouse_list_devices. Check SDK health, the device list, and the reported capabilities. A returnedsdkVersiononly confirms SDK access; it does not prove that hardware control works. Confirm the visible result of any requested mouse action before relying on it.
For a client that accepts the mcpServers JSON format, add this entry manually, replacing the path with your extracted folder. Other clients may require a different configuration format.
Manual configuration does not run the installer's ASR setup. Configure a speech provider separately if you need voice dictation; see Voice dictation.
For source development, npm ci, npm run build, and npm test install dependencies, build TypeScript, and run the default tests. They do not produce a complete shared-v2 native bundle. A complete public shared-v2 packaging workflow is not yet provided. The shared-v2 development and maintenance notes (Chinese) and native host build notes (Chinese) are references for that separate development path.
Reference demos
The mouse lab recording demonstrates the shared-v2 source implementation, not the legacy ZIP installation.
Hardware mouse driving a real browser lab page (gold arrow = system cursor overlaid on the recording) — counters, wheel and hit feedback all come from real browser events:
Voice typing: speak, and it lands in any window
Hold the device voice key, speak, release — the recognized text is typed into whatever window currently has focus. Both clips recorded live at 1080p:
Agent client (terminal) — spoken command typed in and executed:
mcp/acceptance/demo/voice-typing-agent.mp4
WeChat — spoken message typed into the input box and sent:
mcp/acceptance/demo/voice-typing-wechat.mp4
Shared-v2 capabilities (source implementation)
Model → MCP host → shared daemon (
:47192) → C++ native host → USB HID0xF0/0xF1→ uMouse device → Windows input pipeline
- Hardware actions:
umouse_mouse_action— move / click / scroll / drag in desktop physical-pixel coordinates, multi-monitor with negative coords, optionalprecision: standard | high. - Task exclusivity:
umouse_controlbegin → actions → end; only one task drives the mouse and keyboard at a time; dead connections are cleaned up automatically. - Read-only sensors:
umouse_input_status— cursor position, live key state, foreground window identity; read-only, never intercepts. - Voice dictation: mic capture → VAD segmentation → pluggable ASR provider → preview / final transcript; an independent lane that never preempts mouse control (see below).
- Shared daemon: one instance per machine (port 47192), shared across ZCode / Codex / Claude hosts, reclaimed when idle.
Voice dictation: pluggable ASR providers
ASR here is not a black box tied to one vendor — it is a tiny interface contract: implement begin / writePcm / finishInput / cancel and emit preview / segmentFinal / warning / terminal (exactly once), and you have a valid provider. Swapping recognition services means swapping one factory function; mcp/src/sinicloud-asr.ts is a complete reference implementation.
Credentials travel only through configuration and are hot-read per session — swap keys without a restart: by default a JSON file at <data-dir>/sinicloud_asr.json (appId / apiKey / apiSecret / userId / lanid / streamUrl / tokenUrl); environment variables UMSDK_ASR_APP_ID / UMSDK_ASR_API_KEY / UMSDK_ASR_API_SECRET / … override the file. Never hardcoded, never printed, never logged, never committed. The legacy v0.1.0 ZIP ships a trial credential for the open platform; replace it with your own key for production use. The v0.1.1 MCPB contains no cloud credentials and accepts only disabled (default) or windows-speech. See mcp/SHARED-V2.md for the full source provider matrix.
Shared-v2 adaptive positioning
Windows pointer ballistics ("Enhance pointer precision") make the protocol-dots → pixels gain vary with amplitude. umouse-mcp ships an 11-step ballistic gain curve: read-only seeded from local pointer settings on first use of a device, learned online frame-by-frame within [0.125, 10], decaying back to the seed after 60 s idle — no tuning when you change machines or devices; a stale seed costs 1–2 extra frames. Design and measurements: mcp/sdk-host/POSITIONING.md.
Shared-v2 reference acceptance
After preparing a complete shared-v2 build, follow the acceptance setup guide. The lab is in this repository, not the v0.1.0 ZIP.
32 cases verify effects in closed loop on a real browser page: left / right / middle click counts, double-click interval, wheel scrollTop, drag linearity, 1 px bullseye hits.
Shared-v2 security and verification
- Locked screen / UAC / secure desktop: key actions are rejected with
button_feedback_input_desktop_unavailable— that is a safety property, not a bug. effectConfirmedis alwaysfalse: transport success ≠ application effect; the acceptance lab's page evidence is the ground truth.- ASR credentials enter only via local config file and environment variables — never committed, printed or logged;
recoverrequires a human carrying--hardware-reset-confirmed.
Hardware mouse MCP: frequently asked questions
Can I use an ordinary USB or Bluetooth mouse?
No. uMouse MCP needs compatible uMouse hardware and firmware that implement its hardware-control protocol. A normal mouse, a software-only cursor controller, or the SDK version string alone does not establish compatibility. Confirm the device and firmware through hardware support before choosing a package.
Which package should I use with an MCP client?
Use the v0.1.1 MCPB with a client that supports MCPB Node extensions, or the v0.1.0 ZIP and manual configuration for a stdio MCP client. Both require Windows x64, Node.js 22 x64, and compatible hardware. MCPB 0.1.1 packages the legacy 0.1.0 runtime; neither release includes the shared-v2 native host or acceptance lab. Check the installed server's tool list before using source-only examples.
Does this MCP server support macOS or Linux?
The published MCP packages target Windows x64. The separate uMouse SDK has its own platform packages for application integration; those packages do not provide macOS or Linux support for this MCP server.
Can voice dictation work without a cloud ASR service?
The MCPB package defaults to dictation disabled and optionally uses the local windows-speech provider. Other providers, including whisper-cpp, belong to the source provider configuration; they are not all available in MCPB. Local providers need their own runtime, language or model setup. Mouse control does not require enabling a cloud speech provider.
How do I verify that the hardware action actually worked?
Start with umouse_status, umouse_get_capabilities, and umouse_list_devices. Then request an action in a test window and check the cursor and the application's visible response. SDK access and a successful transport receipt are separate from application effects. For a complete shared-v2 source build, use the hardware acceptance lab.
Should I integrate mouse-mcp or mouse-sdk?
Choose this repository to expose hardware mouse actions and voice input to an AI agent through MCP. Choose mouse-sdk to receive device events and audio in your own C/C++, C#, Python, or Electron application. Keep each project's hardware, package, and licensing requirements separate.
Documentation
Hardware & support
Need a compatible device, evaluation unit or firmware check? Contact [email protected] with your target platform, device model, firmware version and intended use case.
Maintained by SonicloudTech (Anhui SoniCloud Intelligent Technology Co., Ltd.) — AI input hardware and the speech open platform.
- Website: https://sinicloud.com/
- Speech open platform: https://open.sinicloud.com/ — powers the default ASR provider; sign up for a trial quota
- Business & technical contact: [email protected] — OEM / distribution / custom firmware / co-development; include the target platform, expected volume, device model, firmware version and intended use case
Related project: uMouse SDK
Integrating smart-mouse hardware into your own application? uMouse SDK provides a C ABI for USB HID/BLE device connections, key events and audio. Start with the English SDK README, integration guide, or SDK downloads. The SDK has its own platform and licensing matrix; those platform options do not extend this MCP server beyond Windows x64. Use the native SDK DLLs bundled with each MCP release rather than substituting a standalone SDK package.
Roadmap
- Cross-machine adaptive gain curves (v0.4)
- Pluggable ASR providers: sinicloud streaming, fully configurable credentials
- Firmware-executed 1–2 count micro-correction frames
- Wheel ACK and scroll-amount closed loop
- Absolute positioning mode
License
The MCP server code is released under the MIT license. The native SDK ships as closed-source DLLs with a public header (include/umouse_sdk.h).
来源:README.md,提交 279feeb
工具
0版本历史
1- v0.1.1最新Oct 23, 2026
评分
已满足适用检查项的 50%
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
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 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15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分