windows-mcp 0.5.8__tar.gz → 0.6.0__tar.gz

windows_mcp-0.6.0/.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: jeogeoalukf
+thanks_dev: gh/jeomon
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/.mcpbignore

@@ -2,4 +2,6 @@
 __pycache__
 build
 dist
-notebook.ipynb
+*.ipynb
+.github
+assets

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: windows-mcp
-Version: 0.5.8
+Version: 0.6.0
 Summary: Lightweight MCP Server for interacting with Windows Operating System.
 Project-URL: homepage, https://github.com/CursorTouch
 Author-email: Jeomon George <jeogeoalukka@gmail.com>
@@ -29,20 +29,17 @@ License-File: LICENSE.md
 Keywords: ai,ai agent,desktop,mcp,windows
 Requires-Python: >=3.13
 Requires-Dist: click>=8.2.1
+Requires-Dist: comtypes>=1.4.15
 Requires-Dist: fastmcp>=2.14.2
 Requires-Dist: fuzzywuzzy>=0.18.0
-Requires-Dist: humancursor>=1.1.5
-Requires-Dist: ipykernel>=6.30.0
 Requires-Dist: markdownify>=1.1.0
-Requires-Dist: pdfplumber>=0.11.7
 Requires-Dist: pillow>=11.2.1
 Requires-Dist: posthog>=7.4.0
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pyautogui>=0.9.54
-Requires-Dist: pygetwindow>=0.0.9
 Requires-Dist: python-dotenv>=1.1.0
 Requires-Dist: python-levenshtein>=0.27.1
-Requires-Dist: pywinauto>=0.6.9
+Requires-Dist: pywin32>=311
 Requires-Dist: requests>=2.32.3
 Requires-Dist: tabulate>=0.9.0
 Requires-Dist: uuid7>=0.1.0
@@ -76,7 +73,8 @@ Description-Content-Type: text/markdown
 mcp-name: io.github.CursorTouch/Windows-MCP
 
 ## Updates
-- Windows-MCP is now available on [PyPI](https://pypi.org/project/windows-mcp/) (thus supports `uvx`)
+- Windows-MCP reached 1M+ Users in [Claude Desktop Extensiosn](https://claude.ai/directory). 
+- Windows-MCP is now available on [PyPI](https://pypi.org/project/windows-mcp/) (thus supports `uvx windows-mcp`)
 - Windows-MCP is added to [MCP Registry](https://github.com/modelcontextprotocol/registry)
 - Try out 🪟[Windows-Use](https://github.com/CursorTouch/Windows-Use)!!, an agent built using Windows-MCP.
 - Windows-MCP is now featured as Desktop Extension in `Claude Desktop`.
@@ -112,13 +110,15 @@ mcp-name: io.github.CursorTouch/Windows-MCP
   Easily adapt or extend tools to suit your unique automation or AI integration needs.
 
 - **Real-Time Interaction**  
-  Typical latency between actions (e.g., from one mouse click to the next) ranges from **0.7 to 2.5 secs**, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
+  Typical latency between actions (e.g., from one mouse click to the next) ranges from **0.4 to 1.2 secs**, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
 
 - **DOM Mode for Browser Automation**  
   Special `use_dom=True` mode for State-Tool that focuses exclusively on web page content, filtering out browser UI elements for cleaner, more efficient web automation.
 
 ## 🛠️Installation
 
+**Note:** When you install this MCP server for the first time it may take a minute or two because of installing the dependencies in `pyproject.toml`. In the first run the server may timeout ignore it and restart it.
+
 ### Prerequisites
 
 - Python 3.13+
@@ -344,17 +344,17 @@ args=[
 
 MCP Client can access the following tools to interact with Windows:
 
-- `Click-Tool`: Click on the screen at the given coordinates.
-- `Type-Tool`: Type text on an element (optionally clears existing text).
-- `Scroll-Tool`: Scroll vertically or horizontally on the window or specific regions.
-- `Drag-Tool`: Drag from one point to another.
-- `Move-Tool`: Move mouse pointer.
-- `Shortcut-Tool`: Press keyboard shortcuts (`Ctrl+c`, `Alt+Tab`, etc).
-- `Wait-Tool`: Pause for a defined duration.
-- `State-Tool`: Combined snapshot of default language, browser, active apps and interactive, textual and scrollable elements along with screenshot of the desktop. Supports `use_dom=True` for browser content extraction (web page elements only) and `use_vision=True` for including screenshots.
-- `App-Tool`: To launch an application from the start menu, resize or move the window and switch between apps.
-- `Shell-Tool`: To execute PowerShell commands.
-- `Scrape-Tool`: To scrape the entire webpage for information.
+- `Click`: Click on the screen at the given coordinates.
+- `Type`: Type text on an element (optionally clears existing text).
+- `Scroll`: Scroll vertically or horizontally on the window or specific regions.
+- `Drag`: Drag from one point to another.
+- `Move`: Move mouse pointer.
+- `Shortcut`: Press keyboard shortcuts (`Ctrl+c`, `Alt+Tab`, etc).
+- `Wait`: Pause for a defined duration.
+- `Snapshot`: Combined snapshot of default language, browser, active apps and interactive, textual and scrollable elements along with screenshot of the desktop. Supports `use_dom=True` for browser content extraction (web page elements only) and `use_vision=True` for including screenshots.
+- `App`: To launch an application from the start menu, resize or move the window and switch between apps.
+- `Shell`: To execute PowerShell commands.
+- `Scrape`: To scrape the entire webpage for information.
 
 ## 🤝 Connect with Us
 Stay updated and join our community:
@@ -367,9 +367,15 @@ Stay updated and join our community:
 
 [![Star History Chart](https://api.star-history.com/svg?repos=CursorTouch/Windows-MCP&type=Date)](https://www.star-history.com/#CursorTouch/Windows-MCP&Date)
 
-## ⚠️Caution
+## 👥 Contributors
+
+Thanks to all the amazing people who have contributed to Windows-MCP! 🎉
+
+<a href="https://github.com/CursorTouch/Windows-MCP/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=CursorTouch/Windows-MCP" />
+</a>
 
-This MCP interacts directly with your Windows operating system to perform actions. Use with caution and avoid deploying it in environments where such risks cannot be tolerated.
+We appreciate every contribution, whether it's code, documentation, bug reports, or feature suggestions. Want to contribute? Check out our [Contributing Guidelines](CONTRIBUTING)!
 
 ## 🔒 Security
 

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/README.md

@@ -26,7 +26,8 @@
 mcp-name: io.github.CursorTouch/Windows-MCP
 
 ## Updates
-- Windows-MCP is now available on [PyPI](https://pypi.org/project/windows-mcp/) (thus supports `uvx`)
+- Windows-MCP reached 1M+ Users in [Claude Desktop Extensiosn](https://claude.ai/directory). 
+- Windows-MCP is now available on [PyPI](https://pypi.org/project/windows-mcp/) (thus supports `uvx windows-mcp`)
 - Windows-MCP is added to [MCP Registry](https://github.com/modelcontextprotocol/registry)
 - Try out 🪟[Windows-Use](https://github.com/CursorTouch/Windows-Use)!!, an agent built using Windows-MCP.
 - Windows-MCP is now featured as Desktop Extension in `Claude Desktop`.
@@ -62,13 +63,15 @@ mcp-name: io.github.CursorTouch/Windows-MCP
   Easily adapt or extend tools to suit your unique automation or AI integration needs.
 
 - **Real-Time Interaction**  
-  Typical latency between actions (e.g., from one mouse click to the next) ranges from **0.7 to 2.5 secs**, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
+  Typical latency between actions (e.g., from one mouse click to the next) ranges from **0.4 to 1.2 secs**, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
 
 - **DOM Mode for Browser Automation**  
   Special `use_dom=True` mode for State-Tool that focuses exclusively on web page content, filtering out browser UI elements for cleaner, more efficient web automation.
 
 ## 🛠️Installation
 
+**Note:** When you install this MCP server for the first time it may take a minute or two because of installing the dependencies in `pyproject.toml`. In the first run the server may timeout ignore it and restart it.
+
 ### Prerequisites
 
 - Python 3.13+
@@ -294,17 +297,17 @@ args=[
 
 MCP Client can access the following tools to interact with Windows:
 
-- `Click-Tool`: Click on the screen at the given coordinates.
-- `Type-Tool`: Type text on an element (optionally clears existing text).
-- `Scroll-Tool`: Scroll vertically or horizontally on the window or specific regions.
-- `Drag-Tool`: Drag from one point to another.
-- `Move-Tool`: Move mouse pointer.
-- `Shortcut-Tool`: Press keyboard shortcuts (`Ctrl+c`, `Alt+Tab`, etc).
-- `Wait-Tool`: Pause for a defined duration.
-- `State-Tool`: Combined snapshot of default language, browser, active apps and interactive, textual and scrollable elements along with screenshot of the desktop. Supports `use_dom=True` for browser content extraction (web page elements only) and `use_vision=True` for including screenshots.
-- `App-Tool`: To launch an application from the start menu, resize or move the window and switch between apps.
-- `Shell-Tool`: To execute PowerShell commands.
-- `Scrape-Tool`: To scrape the entire webpage for information.
+- `Click`: Click on the screen at the given coordinates.
+- `Type`: Type text on an element (optionally clears existing text).
+- `Scroll`: Scroll vertically or horizontally on the window or specific regions.
+- `Drag`: Drag from one point to another.
+- `Move`: Move mouse pointer.
+- `Shortcut`: Press keyboard shortcuts (`Ctrl+c`, `Alt+Tab`, etc).
+- `Wait`: Pause for a defined duration.
+- `Snapshot`: Combined snapshot of default language, browser, active apps and interactive, textual and scrollable elements along with screenshot of the desktop. Supports `use_dom=True` for browser content extraction (web page elements only) and `use_vision=True` for including screenshots.
+- `App`: To launch an application from the start menu, resize or move the window and switch between apps.
+- `Shell`: To execute PowerShell commands.
+- `Scrape`: To scrape the entire webpage for information.
 
 ## 🤝 Connect with Us
 Stay updated and join our community:
@@ -317,9 +320,15 @@ Stay updated and join our community:
 
 [![Star History Chart](https://api.star-history.com/svg?repos=CursorTouch/Windows-MCP&type=Date)](https://www.star-history.com/#CursorTouch/Windows-MCP&Date)
 
-## ⚠️Caution
+## 👥 Contributors
+
+Thanks to all the amazing people who have contributed to Windows-MCP! 🎉
+
+<a href="https://github.com/CursorTouch/Windows-MCP/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=CursorTouch/Windows-MCP" />
+</a>
 
-This MCP interacts directly with your Windows operating system to perform actions. Use with caution and avoid deploying it in environments where such risks cannot be tolerated.
+We appreciate every contribution, whether it's code, documentation, bug reports, or feature suggestions. Want to contribute? Check out our [Contributing Guidelines](CONTRIBUTING)!
 
 ## 🔒 Security
 

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/SECURITY.md

@@ -74,7 +74,7 @@ If you must use Windows-MCP on a regular system:
 2. **Regular Backups**: Maintain frequent, verified backups of all important data
 3. **Network Isolation**: Disconnect from production networks or use firewall rules
 4. **Supervised Operation**: Always monitor the agent's actions in real-time
-5. **Disable High-Risk Tools**: Remove or restrict access to PowerShell-Tool and other destructive tools
+5. **Disable High-Risk Tools**: Remove or restrict access to Shell and other destructive tools
 6. **Test First**: Thoroughly test workflows in a safe environment before production use
 
 ## Security Considerations
@@ -97,11 +97,11 @@ These tools can make permanent changes to your system:
 
 | Tool | Risk | Description |
 |------|------|-------------|
-| **Powershell-Tool** | Critical | Can execute arbitrary PowerShell commands, including system modifications, file deletions, and network operations |
-| **Click-Tool** | High | Can trigger destructive UI actions (delete confirmations, system dialogs) |
-| **Type-Tool** | High | Can overwrite text, potentially destroying data when `clear=True` |
-| **Drag-Tool** | High | Can move/reorganize files, potentially overwriting existing files |
-| **Shortcut-Tool** | High | Can execute destructive keyboard shortcuts (Ctrl+D delete, Alt+F4 close) |
+| **Shell** | Critical | Can execute arbitrary PowerShell commands, including system modifications, file deletions, and network operations |
+| **Click** | High | Can trigger destructive UI actions (delete confirmations, system dialogs) |
+| **Type** | High | Can overwrite text, potentially destroying data when `clear=True` |
+| **Drag** | High | Can move/reorganize files, potentially overwriting existing files |
+| **Shortcut** | High | Can execute destructive keyboard shortcuts (Ctrl+D delete, Alt+F4 close) |
 
 #### **Medium-Risk Tools** (Modifying but Non-Destructive)
 
@@ -109,9 +109,9 @@ These tools modify system state but are generally safe:
 
 | Tool | Risk | Description |
 |------|------|-------------|
-| **App-Tool** | Medium | Launches/manages applications but doesn't modify data |
-| **Scroll-Tool** | Low | Only changes viewport position |
-| **Move-Tool** | Low | Only positions mouse cursor |
+| **App** | Medium | Launches/manages applications but doesn't modify data |
+| **Scroll** | Low | Only changes viewport position |
+| **Move** | Low | Only positions mouse cursor |
 
 #### **Low-Risk Tools** (Read-Only)
 
@@ -119,9 +119,9 @@ These tools only read information without making changes:
 
 | Tool | Risk | Description |
 |------|------|-------------|
-| **State-Tool** | Safe | Only captures desktop state and screenshots |
-| **Wait-Tool** | Safe | Only pauses execution |
-| **Scrape-Tool** | Safe* | Fetches web content (*may expose browsing activity) |
+| **Snapshot** | Safe | Only captures desktop state and screenshots |
+| **Wait** | Safe | Only pauses execution |
+| **Scrape** | Safe* | Fetches web content (*may expose browsing activity) |
 
 ## Best Practices
 
@@ -140,7 +140,7 @@ These tools only read information without making changes:
 ### 3. **Monitor Tool Usage**
 
 - Regularly review logs to understand what actions are being performed
-- Be especially vigilant with high-risk tools (Powershell-Tool, Click-Tool, etc.)
+- Be especially vigilant with high-risk tools (Shell, Click, etc.)
 - Set up alerts for unexpected or suspicious activity
 
 ### 4. **Network Security**
@@ -152,8 +152,8 @@ These tools only read information without making changes:
 
 ### 5. **Data Protection**
 
-- Be aware that **State-Tool** captures screenshots that may contain sensitive information
-- **Scrape-Tool** may fetch content from untrusted websites
+- Be aware that **Snapshot** captures screenshots that may contain sensitive information
+- **Scrape** may fetch content from untrusted websites
 - Avoid using Windows-MCP in environments with highly sensitive data
 - Consider disabling screenshot functionality (`use_vision=False`) when handling confidential information
 

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/manifest.json

@@ -1,9 +1,9 @@
 {
   "manifest_version": "0.2",
   "name": "Windows-MCP",
-  "version": "0.5.8",
+  "version": "0.5.7",
   "description": "MCP Server that enables Claude to interact with Windows OS",
-  "long_description": "Windows MCP is an open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server bridges the gap between LLMs and the Windows operating system, allowing agents to perform tasks such as **file navigation, application control, UI interaction, QA testing,** and more.\\n\\n## Key Features\\n\\n- **Seamless Windows Integration**: Interacts natively with Windows UI elements, opens apps, controls windows, simulates user input, and more.\\n- **Use Any LLM (Vision Optional)**: Unlike many automation tools, Windows MCP doesn't rely on any traditional computer vision techniques or specific fine-tuned models; it works with any LLMs, reducing complexity and setup time.\\n- **Rich Toolset for UI Automation**: Includes tools for basic keyboard, mouse operation and capturing window/UI state.\\n- **Lightweight & Open-Source**: Minimal dependencies and easy setup with full source code available under MIT license.\\n- **Customizable & Extendable**: Easily adapt or extend tools to suit your unique automation or AI integration needs.\\n- **Real-Time Interaction**: Typical latency between actions (e.g., from one mouse click to the next) ranges from **1.5 to 2.3 secs**, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.\\n\\n## Requirements\\n\\n### UV Package Manager\\nThis MCP server requires [UV](https://github.com/astral-sh/uv), a fast Python package manager. \\n\\n```bash\\npip install uv\\n```\\n\\nFor detailed installation instructions, see the [UV documentation](https://github.com/astral-sh/uv#installation).",
+  "long_description": "Windows MCP is an open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server, it bridges the gap between large language models (LLMs) and the Windows OS, allowing agents to perform tasks such as **file navigation, application control, UI interaction, QA testing, and more**.\n\n**KEY FEATURES**\n- **Seamless Windows Integration**: Interacts natively with Windows UI elements, opens applications, controls windows, simulates user input, and more.\n- **Use Any LLM (Vision Optional)**: Does not rely on traditional computer vision techniques or fine-tuned models. Works with any LLM, reducing complexity and setup time.\n- **Rich Toolset for UI Automation**: Includes tools for keyboard and mouse control, window management, and capturing window or UI state.\n- **Lightweight & Open-Source**: Minimal dependencies with full source code available under the MIT license.\n- **Customizable & Extendable**: Easily adapt or extend tools to suit custom automation workflows or AI integrations.\n- **Real-Time Interaction**: Typical latency between actions ranges from `0.4` to `1.2` seconds, depending on system load, active applications, and LLM inference speed.\n\n**MINIMUM REQUIREMENTS**\n- Python 3.13 or higher\n- UV Package Manager\nThis MCP server requires UV, a fast Python package manager.\nInstallation:\n`curl -LsSf https://astral.sh/uv/install.sh | sh`\nFor detailed installation instructions, [see the UV documentation](https://github.com/astral-sh/uv)",
   "author": {
     "name": "CursorTouch",
     "url": "https://cursortouch.com/"

{windows_mcp-0.5.8 → windows_mcp-0.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "windows-mcp"
-version = "0.5.8"
+version = "0.6.0"
 description = "Lightweight MCP Server for interacting with Windows Operating System."
 authors = [
     { name = "Jeomon George", email = "jeogeoalukka@gmail.com" }
@@ -12,20 +12,17 @@ keywords = ["windows", "mcp", "ai", "desktop","ai agent"]
 requires-python = ">=3.13"
 dependencies = [
     "click>=8.2.1",
+    "comtypes>=1.4.15",
     "fastmcp>=2.14.2",
     "fuzzywuzzy>=0.18.0",
-    "humancursor>=1.1.5",
-    "ipykernel>=6.30.0",
     "markdownify>=1.1.0",
-    "pdfplumber>=0.11.7",
     "pillow>=11.2.1",
     "posthog>=7.4.0",
     "psutil>=7.0.0",
     "pyautogui>=0.9.54",
-    "pygetwindow>=0.0.9",
     "python-dotenv>=1.1.0",
     "python-levenshtein>=0.27.1",
-    "pywinauto>=0.6.9",
+    "pywin32>=311",
     "requests>=2.32.3",
     "tabulate>=0.9.0",
     "uuid7>=0.1.0",