WSLSnapit-MCP

WSLSnapit-MCP is a handy tool that lets AI assistants "see" what’s happening on a Windows computer, even if they are running inside a Linux-based environment like WSL (Windows Subsystem for Linux). It bridges the gap between these two systems, allowing an AI to take screenshots of the screen or read whatever is currently copied to the clipboard. This makes it much easier for an AI to help troubleshoot software, explain what is appearing on a user's screen, or quickly grab text and images to assist with a task. For more specific needs, this MCP server offers granular control over exactly what context is shared. It can target specific monitors in a multi-screen setup, find windows by their titles, or even isolate a specific application by its process name. When reading the clipboard, it intelligently detects whether the content is text or an image and delivers it in the appropriate format. This flexibility ensures the AI gets exactly the visual information it needs without the user having to manually save and upload files. Under the hood, the server is built for performance and reliability within the Model Context Protocol ecosystem. It uses a PowerShell bridge to communicate between WSL and the Windows API and employs the Sharp image processing library to handle heavy lifting. To ensure smooth interaction with LLMs, it features "smart compression" that progressively adjusts image quality and resolution to stay under the 1MB limit common in AI message protocols. This combination of DPI-awareness and optimized data transfer makes it a robust solution for developers building vision-capable AI agents in hybrid Windows/Linux workflows.

Category: Cloud & Infrastructure

Tags: automation, clipboard, screenshot, windows, wsl

Visit WSLSnapit-MCP

How to install and configure WSLSnapit-MCP

1. Installation Prerequisites: * Windows 10/11 with WSL2 installed * Node.js 18.0.0 or higher * npm, yarn, or bun package manager * PowerShell (included with Windows) Steps: bash # Clone the repository git clone https://github.com/peterparker57/WSLSnapit-MCP.git cd WSLSnapit-MCP # Install dependencies npm install # or yarn install # or bun install

2. Configuration Add the following configuration to your Claude Desktop configuration file: * Windows: %APPDATA%\Claude\claude_desktop_config.json * macOS: ~/Library/Application Support/Claude/claude_desktop_config.json * Linux: ~/.config/Claude/claude_desktop_config.json json { "mcpServers": { "wslsnapit": { "command": "wsl", "args": [ "--cd", "/mnt/h/dev/mcp/wslsnapit-mcp", "node", "index.js" ] } } } Note: Ensure you adjust the path /mnt/h/dev/mcp/wslsnapit-mcp to the actual directory where you installed the server.

3. Available Tools

take_screenshot Captures screenshots of monitors or specific windows. * filename (string): Filename when saving to disk (default: "screenshot.png") * monitor (string|number): "all", "primary", or specific monitor number (default: "all") * windowTitle (string): Capture window by title (partial match) * windowIndex (number): Which window to capture if multiple match (default: 1) * processName (string): Capture window by process name * folder (string): Custom folder path (supports WSL and Windows paths) * returnDirect (boolean): Return image to AI or save to disk (default: true) * quality (number): JPEG quality (1-100) for direct return (default: 80)

read_clipboard Reads text or images from the Windows clipboard. * format (string): Format to read: "auto", "text", or "image" (default: "auto")

4. Example Prompts Screenshot Usage: * "Take a screenshot of my primary monitor." * "Capture the window with 'Visual Studio' in the title." * "Take a screenshot of the 'notepad' process." * "Capture monitor 2 and save it as 'desktop.png' in /home/user/screenshots." Clipboard Usage: * "Read the current content of my Windows clipboard." * "Check if there is an image on my clipboard and show it to me." * "Get the text currently copied on Windows."

What you can do with WSLSnapit-MCP

Use Case 1: Visual Debugging of Windows-hosted Web Applications Problem: Developers working in WSL often run their development servers in the Linux environment, but preview the application in a Windows-based browser (like Chrome or Edge). When a UI bug occurs, it is cumbersome to manually take a screenshot, save it, and upload it to an AI assistant for debugging. Solution: The AI assistant can use the take_screenshot tool with windowTitle: "Chrome" to directly capture the browser window. The built-in smart compression ensures the image is optimized for the LLM's context window, allowing the AI to "see" the CSS layout issues or console errors alongside the code in WSL. Example: A developer tells the AI: "The layout of my header is broken in Chrome. Can you look at it?" The AI captures the Chrome window, analyzes the visual alignment, and suggests the necessary CSS fixes in the WSL-based repository.

Use Case 2: AI-Powered Analysis of Clipboard Data Problem: Users often find interesting snippets of text, data tables in PDFs, or even images of diagrams while browsing on Windows that they want to process using an AI assistant configured in their WSL environment. Manually pasting large amounts of data or saving images to share them can break the flow. Solution: This MCP allows the AI to use read_clipboard to instantly pull whatever is currently copied on the Windows host. Whether it’s a block of code, a snippet of documentation, or an image of a graph, the AI can ingest it directly from the Windows system memory. Example: A user copies a complex JSON object from a Windows Slack message and says to their WSL-based AI: "I just copied a JSON object; can you write a TypeScript interface for it?" The AI reads the clipboard, detects the text, and generates the interface immediately.

Use Case 3: Guided Troubleshooting for Windows Software from WSL Problem: When a user encounters an error in a Windows-specific application (like a database manager or a specialized IDE) while working in WSL, explaining the state of the GUI to an AI assistant is difficult and prone to missing details. Solution: The MCP enables the AI to target specific Windows processes using processName. The AI can capture the specific application's window to identify error messages, icon states, or configuration settings that the user might have missed. Example: A user says, "My Windows Docker Desktop is showing an…

Key facts

• Open Source
• Cloud & Infrastructure, Design, Media & Creative, Developer Tools & Code Intelligence
• automation, clipboard, screenshot, windows, wsl

Part of MCP Servers

Related MCP servers

• MCP KQL Server — Execute KQL queries using Azure authentication. Requires Azure CLI login.
• MCP LaTeX Server — Create, edit, and manage LaTeX files. Requires an external LaTeX distribution like MiKTeX, TeX Live, or MacTeX.
• MCP JSON — A collection of servers for file system operations, Google search, web automation, and executing terminal commands.
• MCP Jupyter Complete — A server for Jupyter notebook manipulation with position-based operations and VS Code integration.
• MCP LSP Go — An MCP server that connects AI assistants to Go's Language Server Protocol (LSP) for advanced code analysis.
• MCP Manager — A full-stack application for managing Model Context Protocol (MCP) servers for Claude Desktop with a modern web interface.