Screenshot

Provides a screenshot capture service via MCP for WSL, supporting monitor/window/process targeting and flexible save paths.
  • javascript

3

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "peterparker57-screenshot-mcp": {
      "command": "node",
      "args": [
        "/path/to/screenshot-mcp/index.js"
      ]
    }
  }
}

You can capture Windows screenshots directly from your MCP-enabled AI assistant running in WSL. This MCP server opens a path from Claude to a powerful screenshot tool that supports full desktop captures, monitor selection, window- and process-based captures, and flexible save locations with automatic path conversion between WSL and Windows.

How to use

Install and run the MCP server, then invoke the take_screenshot tool from your Claude session. You can capture the entire desktop, a specific monitor, a particular window by title, or a window by its process name. Save the resulting image to a custom folder or rely on the default storage location.

How to install

Prerequisites before you begin: Windows with WSL installed and Node.js available inside WSL. You also need Claude Desktop or Claude Code with MCP support.

Step 1: Clone the MCP server repository and enter the project directory.

git clone https://github.com/peterparker57/screenshot-mcp.git
cd screenshot-mcp

Step 2: Install dependencies using npm. You can also use bun if you prefer, but npm is the supported option shown in the example.

npm install

Step 3: Add the MCP server to your Claude configuration so Claude can call the screenshot tool. Include the command to run the server and the argument that points to the main script.

{
  "mcpServers": {
    "screenshot": {
      "command": "node",
      "args": [
        "/path/to/screenshot-mcp/index.js"
      ],
      "disabled": false,
      "alwaysAllow": [
        "take_screenshot"
      ]
    }
  }
}

Additional configuration and usage notes

The server saves screenshots by default to workspace/screenshots/, but you can specify a custom folder when calling the tool. You can also capture in DPI-aware mode to ensure proper scaling on high-DPI displays. The tool supports capturing by monitor, window title, or process name, and it can elevate window padding to include shadows and borders for a fuller image.

Usage patterns and examples

Basic usage: Tell Claude to take a screenshot without extra options, and it will save to the default location.

Capture a specific monitor: Ask for a screenshot of monitor 1 or the primary monitor.

Capture a window by title: Request a screenshot of a window titled with a partial or full match, such as "Chrome" or "Visual Studio Code".

Capture by process: Request a screenshot of a window belonging to a process like notepad.exe or chrome.

Troubleshooting and notes

If a screenshot fails, verify that the window or process exists and is visible. The server can create missing directories automatically and converts paths between WSL and Windows formats as needed.

If you encounter PowerShell or path conversion issues, ensure you can reach the Windows environment from WSL and that your permissions allow writing to the target folder.

Available tools

take_screenshot

Single MCP tool to capture screenshots with options for monitor, window title, process name, file name, and save location. Includes automatic path conversion and DPI-aware rendering.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational