Little Mouse Pointer
Provides Windows desktop UI context to OpenAI Codex, enabling AI agents to select windows, UI elements, or screen regions and receive UI Automation, screenshot, and OCR data.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Little Mouse Pointerhover over the save button and tell me its properties"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Little Mouse Pointer
This repository provides Little Mouse Pointer: a Windows desktop UI context picker for AI agents. Users can select windows, UI elements, or screen regions with the mouse, obtain context via UI Automation, screenshots, and native OCR, and after confirmation, provide it to OpenAI Codex, DeepSeek Harness, or other compatible clients through MCP.
The plugin directory is plugins/little-mouse-pointer. See the README in the plugin directory for full features, protocol, and runtime instructions.
Documentation Navigation
Getting Started Tutorial: the complete flow for first installation, first selection, and common issues.
Installation Checklist for Beginners: confirm item by item for Codex, DeepSeek Harness, and manual run scenarios.
Plugin Full README: features, usage flow, privacy limitations, and failure boundaries.
Runtime Notes: self-contained runtime package,
run.ps1, and MCP stdio behavior.DeepSeek Harness Configuration: manual Cordis configuration when the bundle is unavailable.
Protocol Notes: tool output fields and confirmation flow.
Related MCP server: atomic-computer-mcp
Installing from GitHub into Codex
Run the following command in PowerShell, replacing OWNER/REPOSITORY with the actual GitHub repository:
codex plugin marketplace add OWNER/REPOSITORY --ref main
codex plugin add little-mouse-pointer@auto-mouseIf you only need to download the plugin directory, you can use the GitHub release zip, or install the plugins/little-mouse-pointer layer locally. Do not mistake the repository root for the direct plugin root.
Connecting to DeepSeek Harness
Copy the Chinese installation checklist or the English installation checklist, then refer to the DeepSeek Harness Configuration and change the paths to your actual directories. MCP stdio must be launched directly:
plugins/little-mouse-pointer/app/MousePointer.Windows.exeDo not use run.ps1 as an MCP stdio bridge; run.ps1 is only for manually launching the GUI and self-test.
Installing the Harness bundle directly from GitHub
The repository root also provides an installation package conforming to the Harness dsh.bundle specification. It is recommended to pin a release tag:
dsh plugin --profile demo add github:Fish121380/auto-mouse#v0.1.1
dsh --profile demo --dump-configThe bundle automatically locates the Windows x64 exe it carries and registers @deepseek-ai/dsh-mcp-client. It only works on Windows x64; the port can be overridden in the profile's cordis.patch.yml:
- replace:
- id: little-mouse-pointer
config:
port: 49154Pre-installation Checks
Windows 10/11 x64.
No .NET installation required; the release package is self-contained.
Keep all files in
plugins/little-mouse-pointer/app.The default port is
49153; the endpoint andMOUSE_POINTER_HTTP_PORTmust match.Close old Little Mouse Pointer instances before running Codex/Harness.
The MCP tools are
ui_context_pick,ui_context_current,ui_context_clear.
This server cannot be installed
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 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
- AlicenseAqualityAmaintenanceAllows AI clients to see and control Windows 10/11 desktops via MCP, with screenshots, UI Automation, Chrome CDP, keyboard/mouse, and terminal using semantic element targeting.30354MIT
- AlicenseNot gradedqualityAmaintenanceEnables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.1MIT
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
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/Fish121380/auto-mouse'
If you have feedback or need assistance with the MCP directory API, please join our Discord server