Skip to main content
Glama

WinMind

CI License: Apache-2.0 Platform: Windows 10/11 Python 3.10+ MCP Tools: 222

A Windows MCP server that lets an AI see and drive any app through the accessibility tree - no screenshots, no mouse, no pixel guessing - plus 200+ native Windows tools.

Most computer-use agents look at the screen: take a screenshot, send thousands of image tokens to a model, guess coordinates, click, take another screenshot. WinMind reads what Windows already knows. Every app publishes its buttons, text boxes, lists and text to UI Automation, the accessibility layer screen readers like Narrator and NVDA use. WinMind turns that into a compact, numbered tree an AI can read in one call and act on in the next - even when the app is behind other windows.

WhatsApp  (WhatsApp.Root.exe, window)
├─ [6] banner
│  ├─ [7] button "Chats" (42) checked [toggle]
│  ├─ [8] button "Calls" (4) unchecked [toggle]
├─ [20] textbox "Search or start a new chat" [set_value]
├─ [21] tabs "chat-list-filters" (4)
│  ├─ [22] tab "All" selected [select]
│  ├─ [23] tab "Unread 42" [select]
├─ [26] grid "Chat list" (9)
│  ├─ [29] row "Alex Yesterday Photo" [click]
│  ├─ [30] row "Study Group 3 unread messages Yesterday" [click]
└─ [37] button "Send document" [click]

ui_act(ref=30) opens that chat. ui_act(name="Play", title_contains="spotify") plays music. No screenshot was taken.

Why it's different

Screenshot agents

WinMind

What the model gets

images (thousands of tokens each)

a text tree with real names, states and actions

Speed per look

seconds (capture + vision model)

0.1-0.3 s for a whole app (one cross-process call)

Clicking

pixel coordinates, moves your mouse

the app's own accessibility actions - your mouse never moves

Apps behind other windows

must bring them to front

reads and acts in the background

Text in editors/documents

OCR

exact text from the app (TextPattern)

Things WinMind handles that trip up simpler UI Automation tools (details in docs/ARCHITECTURE.md):

  • Chromium-based apps behind other windows (Discord, Spotify, Steam, Teams, VS Code) expose no content while covered - Chromium's occlusion tracking pauses them. WinMind wakes them properly once; the tree then stays readable in the background. It never pulls a window over a full-screen game.

  • WinUI 3 apps that host WebView2 (WhatsApp) loop back into their own web content - naive scans fetch the same elements thousands of times. WinMind splits and de-duplicates: 7.3 s -> 0.25 s.

  • Web clicks that silently do nothing: pressing a list item whose click handler sits on an inner link. WinMind performs the default action of the element that really owns the click - without moving the mouse.

  • Buttons and text in one tree: editor/document content comes through next to the controls.

  • Finds apps by process, not just title (Spotify's title is the song playing), including apps hidden in the tray.

  • Token budget: 222 tool definitions cost ~32k tokens (143 per tool); long outputs are trimmed with a note saying what was cut; errors are one actionable line, not tracebacks.

Related MCP server: Windows-MCP

What's in the box (222 tools)

Area

Examples

UI automation

ui_tree, ui_map, ui_act, ui_read, ui_find_text, ui_element_at, ui_focused

Health & diagnostics

full_health_scan, why_is_my_pc_slow, smart_disk_health, battery_health, reliability_records

Hardware & gaming

CPU/GPU metrics, temperatures, fans, FPS / frame times / stutter / GPU-bottleneck (PresentMon)

Live OS tracing

ETW process / DNS / file / network events

Network

why_no_internet, port_process_map, whats_on_port, DNS cache, Wi-Fi scan

Privacy & security

whats_using_my_webcam / _mic, Defender, BitLocker, USB history, startup entries

Windows & desktops

windows, virtual desktops, saved workspaces

Files, processes, services, registry

with guards against system folders, critical keys and core OS processes

Display, audio, media, speech

per-app volume, now-playing + media control, brightness, night light, TTS

Screen capture (explicit only)

capture_window_image renders one window even when it's covered

Full list with one line per tool: TOOLS.md. An AI can also call tool_guide for a categorized index.

Quick start

One-click: Claude Desktop

Download winmind-mcp-<version>.mcpb from Releases and open it - Claude Desktop installs it like a browser extension (it needs uv, which sets up the Python dependencies for you). The bundle includes the native helpers.

Any MCP client (Claude Code, Cursor, VS Code, local models...)

Requirements: Windows 10/11, Python 3.10+.

git clone https://github.com/jhonpork1233-beep/win-mind
cd win-mind
pip install -e .

Add it to your MCP client. Use the full path to Python so a changed PATH can never break it:

// Claude Desktop / Claude Code (~/.claude.json "mcpServers") / any MCP client
{
  "winmind": {
    "command": "C:\\Path\\To\\Python\\python.exe",
    "args": ["-m", "winmind"]
  }
}

Claude Code shortcut: claude mcp add winmind -- "C:\Path\To\Python\python.exe" -m winmind

Then ask things like "what's in my WhatsApp unread chats?", "play my liked songs on Spotify", "why is my PC slow?", "screenshot Notepad without switching windows".

Optional native helpers

The core (UI engine, files, processes, registry, health, network...) is pure Python. Some tools use small native helpers - live event hooks, ETW, window streaming, virtual desktops, the WinRT broker (media, notifications), HUD overlays, PresentMon. Build them from source in native/:

powershell -ExecutionPolicy Bypass -File scripts\build_all.ps1

(Visual Studio 2022 Build Tools with the C++ workload and Windows SDK; MinGW g++ for winmind_native.dll.) Tools whose helper isn't built say so and name the script to run.

Using it efficiently (for AI clients and prompt writers)

  • Start with ui_tree (structure) or ui_read (just the text) - not screenshots.

  • Act by name when it's unambiguous: ui_act(name="Search", title_contains="spotify"); by ref otherwise.

  • Prefer summary tools (full_health_scan, system_health_summary, windows_summary) over raw listings (appx_packages, service_list, port_process_map).

  • Every tool accepts detail=true (no trimming), compact=true (short keys).

  • Clients with deferred tool loading (e.g. Claude Code's tool search) only load the definitions they use.

Safety

WinMind runs with your user's rights and can change your system - that's its purpose. Read SECURITY.md.

  • Every tool carries MCP risk annotations (readOnlyHint, destructiveHint) so clients can ask before risky calls; 16 tools are marked destructive.

  • Built-in guards: file tools refuse Windows/System32/Program Files and drive roots; registry writes/deletes refuse critical keys; process tools refuse core OS processes.

  • The UI engine never takes screenshots and never moves the mouse. Screen capture exists only as explicit tools.

  • No telemetry. Everything WinMind writes stays in %LOCALAPPDATA%\WinMind (override with WINMIND_HOME).

  • Run it non-elevated unless you need admin-only tools.

Testing

pip install -e .[dev]
python tests\audit_tools.py tests\audit.json     # calls every safe tool, sandbox-tests the write tools
python tests\audit_summary.py tests\audit.json

The audit only writes to a temp folder, the throwaway registry key HKCU\Software\WinMindAudit, a process it starts itself and its own Notepad window. Current results: 102/109 read-only tools OK (the rest need admin rights, a running session or an open Office document), 37/37 sandbox and guard tests pass.

Roadmap

  • Java Access Bridge (Java/Swing apps), IAccessible2 text for Firefox/LibreOffice

  • Stable selectors and recorded workflows

  • Live UI event stream (tree deltas instead of re-reading)

  • UI Automation Remote Operations for even faster trees

  • One-click installs: Claude Desktop extension, Windows agent connector (On-Device Registry)

  • Public head-to-head benchmark against other Windows MCP servers

License

Apache-2.0. Third-party components: THIRD_PARTY_NOTICES.md.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to interact with Windows operating systems through native UI automation, file navigation, application control, and system commands. Provides seamless integration between LLMs and Windows environments for tasks like clicking, typing, launching apps, and capturing desktop state.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to interact with Windows operating systems by providing tools for UI automation, file navigation, application control, and system operations. Works with any LLM to perform tasks like clicking, typing, launching applications, and executing PowerShell commands through native Windows integration.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to control Windows systems using AutoHotkey v2 and the UI Automation accessibility tree for efficient, text-based computer interaction. It provides tools for window management, keystrokes, and UI inspection while significantly reducing token costs compared to screenshot-based approaches.
    8
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to control Windows systems through natural language commands, providing 200+ automation tools for system control, file operations, web automation, and more.
    56
    MIT