Little Mouse Pointer
Enables AI agents to select Windows desktop UI elements, windows, or screen regions via mouse hover, then obtain context through UI Automation, screenshots, and local OCR for MCP-compatible clients.
README
Little Mouse Pointer
本仓库提供 Little Mouse Pointer:一个面向 AI agent 的 Windows 桌面 UI context picker。用户可以用鼠标选择窗口、UI 元素或屏幕区域,通过 UI Automation、截图和本机 OCR 获取上下文,并在确认后通过 MCP 提供给 OpenAI Codex、DeepSeek Harness 或其他兼容客户端。
插件目录为 plugins/little-mouse-pointer。完整功能、协议和运行时说明见插件目录中的 README。
文档导航
- 新手教程:第一次安装、首次选取和常见问题的完整流程。
- 新手安装检查表:按 Codex、DeepSeek Harness 和手动运行场景逐项确认。
- 插件完整 README:功能、使用流程、隐私限制和故障边界。
- 运行时说明:self-contained 运行包、
run.ps1和 MCP stdio 行为。 - DeepSeek Harness 配置:bundle 不可用时的手工 Cordis 配置。
- 协议说明:工具输出字段和确认流程。
从 GitHub 安装到 Codex
在 PowerShell 中执行下面的命令,把 OWNER/REPOSITORY 替换成实际 GitHub 仓库:
codex plugin marketplace add OWNER/REPOSITORY --ref main
codex plugin add little-mouse-pointer@auto-mouse
如果只需要下载插件目录,可以使用 GitHub release zip,或在本地安装 plugins/little-mouse-pointer 这一层。不要把仓库根目录误当成直接插件根目录。
接入 DeepSeek Harness
复制 中文安装检查表 或 English installation checklist,再参考 DeepSeek Harness 配置,把路径改成实际目录。MCP stdio 必须直接启动:
plugins/little-mouse-pointer/app/MousePointer.Windows.exe
不要通过 run.ps1 作为 MCP stdio bridge;run.ps1 只用于手动启动 GUI 和 self-test。
从 GitHub 直接安装 Harness bundle
仓库根目录同时提供符合 Harness dsh.bundle 规范的安装包。建议固定发行版 tag:
dsh plugin --profile demo add github:Fish121380/auto-mouse#v0.1.1
dsh --profile demo --dump-config
该 bundle 会自动定位自己携带的 Windows x64 exe,并注册 @deepseek-ai/dsh-mcp-client。它只适用于 Windows x64;端口可在 profile 的 cordis.patch.yml 中覆盖:
- replace:
- id: little-mouse-pointer
config:
port: 49154
安装前检查
- Windows 10/11 x64。
- 不需要安装 .NET,发行包已经 self-contained。
- 保留
plugins/little-mouse-pointer/app的全部文件。 - 默认端口为
49153,endpoint 和MOUSE_POINTER_HTTP_PORT必须一致。 - Codex/Harness 运行前关闭旧的 Little Mouse Pointer 实例。
- MCP 工具为
ui_context_pick、ui_context_current、ui_context_clear。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.