Winsight MCP
W

Winsight MCP

Windows Screen Capture MCP Server, allowing Claude Code to capture the desktop, manage windows, and launch applications, supporting full - screen, region, and window screenshots, as well as window control functions.
2.5 points
5.7K

What is WinSight MCP?

WinSight is a Model Context Protocol (MCP) server specifically designed for the Windows system. It allows AI assistants such as Claude Code to directly interact with your Windows desktop, including capturing screenshots, managing window positions and sizes, and launching applications. In simple terms, it equips AI assistants with 'eyes' so that they can 'see' your desktop and perform operations.

How to use WinSight MCP?

Using WinSight is very simple: First, install the server via uvx, pip, or source code. Then, add the server configuration to the Claude Desktop configuration file. After the configuration is complete, you can directly issue instructions to Claude Code in natural language, such as 'Take a screenshot of my screen' or 'Open the calculator and take a screenshot'.

Use Cases

WinSight is particularly suitable for the following scenarios: 1. Automated screen operations and documentation 2. Remote assistance and troubleshooting 3. Application interface testing and verification 4. Teaching demonstrations and step recording 5. Multi - window layout management

Main Features

Full - screen Screenshot
Capture the entire screen or the complete picture of a specified display, supporting multi - display configurations
Window Screenshot
Use the Win32 PrintWindow API to capture the content of a specific window, accurately capturing even if the window is obscured by other windows
Region Screenshot
Select any rectangular area on the screen for precise screenshot, suitable for capturing specific interface elements
Window Management
List, find, move, resize, minimize, maximize, restore, and focus on windows
Display Information
Get detailed information about all displays, including resolution, position, and primary display identification
Application Launch
Launch applications and optionally wait for their windows to appear, supporting automated testing and workflows
Advantages
True window content capture: Accurately take screenshots even when the window is obscured
Complete window control: Support operations such as moving, resizing, minimizing/maximizing
Easy to integrate: Seamlessly integrate with AI assistants such as Claude Code through the MCP protocol
Cross - version compatibility: Support Windows 10 and Windows 11 systems
Open - source and free: Based on the MIT license, can be freely used and modified
Limitations
Windows - only: Does not support macOS or Linux
Requires a Python environment: Requires Python 3.10 or higher
Permission requirements: Some operations may require administrator privileges
Depends on the Windows API: Functionality is limited by the API capabilities of the Windows system
Real - time limitations: There is a slight delay in screenshots and operations

How to Use

Choose an Installation Method
Choose the most suitable installation method according to your needs: - uvx (recommended): Run directly without installation - pip installation: Use the Python package manager - Source code installation: Get the latest version from GitHub
Configure Claude Desktop
Add the WinSight server configuration to the Claude Desktop configuration file. The configuration file is usually located at: - Project directory:.mcp.json - User directory: ~/.claude/claude_desktop_config.json
Restart Claude Desktop
After saving the configuration file, restart the Claude Desktop application for the configuration to take effect
Start Using
Use natural language to issue instructions directly in Claude Code, such as asking 'Take a screenshot of my screen' or 'List all windows'

Usage Examples

Document Screenshot and Annotation
When you need to show someone a software interface or operation steps, you can let the AI assistant automatically take a screenshot and add instructions
Multi - window Layout Management
When you need to use multiple applications simultaneously and want them to be arranged in a specific layout
Application Interface Testing
Developers can automatically test the display effects of application interfaces in different states
Remote Assistance Preparation
Quickly collect system status information before seeking technical support

Frequently Asked Questions

Does WinSight require administrator privileges?
Can I use WinSight on macOS or Linux?
What is the quality and format of the screenshots?
How to ensure privacy and security?
What if the window title is inaccurate?
Does it support multi - display environments?

Related Resources

GitHub Repository
Source code, issue tracking, and the latest version of WinSight MCP
Model Context Protocol Official Website
Understand the technical details and specifications of the MCP protocol
Python Official Website
Download Python 3.10 or higher
Claude Desktop Configuration Guide
Official Claude Desktop configuration documentation
Windows API Documentation
Win32 API reference documentation (for advanced users)

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "winsight": {
      "command": "uvx",
      "args": ["winsight-mcp"]
    }
  }
}

{
  "mcpServers": {
    "winsight": {
      "command": "winsight-mcp"
    }
  }
}

{
  "mcpServers": {
    "winsight": {
      "command": "uv",
      "args": ["--directory", "/path/to/WinSight-MCP", "run", "winsight-mcp"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
6.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
5.4K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.5K
4 points
P
Paperbanana
Python
6.8K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.7K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.0K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.6K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.7K
4.5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.9K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.2K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.4K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase