Windows Screenshots

by sarfraznawaz2005

Not rated
GitHub

About

A Model Context Protocol (MCP) server that provides screenshot capture functionality on Windows systems.

Details

Author
sarfraznawaz2005
Categories
Other, Developer Tools

Setup

Install Windows Screenshots in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/sarfraznawaz2005/mcp-windows-screenshot

Follow the installation instructions in the repository README, then restart your MCP client.

AModel Context Protocol(MCP) server that provides screenshot capture functionality on Windows systems.

- Full-screen screenshots: Capture entire monitors or all monitors
- Region screenshots: Interactive area selection for targeted captures
- Screenshot management: List and manage captured screenshots
- Image embedding: Optional base64 image embedding in MCP responses
- Cross-monitor support: Handle multi-monitor setups

- Windows OS(currently Windows-only)
- Node.js>= 18.0.0
- Helper executable: A Windows executable (RegionSnip.exe) that handles the actual screenshot capture
- Ensure the helper executable exists atbin/RegionSnip.exe

This server communicates via stdio and can be used with any MCP-compatible client (like Claude Desktop).

Or with the MCP inspector for debugging:

You can run this MCP server directly using npx without installing it globally:

{ "mcpServers": { "windows-screenshots": { "command": "npx", "args": ["mcp-windows-screenshot"] } } }

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "windows-screenshots": { "command": "npx", "args": ["mcp-windows-screenshot"] } } }

Add to your~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "windows-screenshots": { "command": "npx", "args": ["mcp-windows-screenshot"] } } }

- mode: Always "full" (default)
- allMonitors: Capture all monitors (default: true)
- monitor: Specific monitor number (optional)
- includeImage: Embed image as base64 in response (default: false)
- timeoutMs: Timeout in milliseconds (default: 60000)

{ "mode": "full", "allMonitors": true, "includeImage": true }
{ "ok": true, "cancelled": false, "path": "screenshots/full-2024-01-14T10-53-52-000Z.png", "rect": {"x": 0, "y": 0, "width": 1920, "height": 1080}, "width": 1920, "height": 1080, "mode": "full", "allMonitors": true, "monitor": null }

Allows interactive selection of a screen region to capture.

- mode: Always "region" (default)
- includeImage: Embed image as base64 in response (default: false)
- timeoutMs: Timeout in milliseconds (default: 120000)

{ "ok": true, "cancelled": false, "path": "screenshots/region-2024-01-14T10-53-52-000Z.png", "rect": {"x": 100, "y": 100, "width": 800, "height": 600}, "width": 800, "height": 600, "mode": "region" }

Lists saved screenshots in the screenshots directory.

- limit: Maximum number of screenshots to return (default: 50, max: 200)

{ "items": [ { "path": "screenshots/region-2024-01-14T10-53-52-000Z.png", "sizeBytes": 245760, "createdAt": "2024-01-14T10:53:52.000Z" } ] }

The server requires a helper executable atbin/RegionSnip.exethat supports the following command-line arguments:

- --mode full|region: Capture mode
- --out <path>: Output file path
- --all: Capture all monitors (full mode only)
- --monitor <n>: Specific monitor number (full mode only)

The executable should output JSON to stdout with the following structure:

{ "ok": true, "cancelled": false, "rect": {"x": 0, "y": 0, "width": 1920, "height": 1080}, "width": 1920, "height": 1080 }

Screenshots are automatically saved to thescreenshots/directory in the project root. This directory is created automatically if it doesn't exist.

The server can be tested using the MCP inspector:

This starts the server and opens a debugging interface to test the available tools.

├── src/ │ └── index.ts # Main server implementation ├── build/ # Compiled JavaScript output ├── screenshots/ # Screenshot storage directory ├── bin/ │ └── RegionSnip.exe # Helper executable (not included) ├── package.json └── README.md

Challenge-response quality verification for AI agents and MCP servers.

This MCP server enabling AI agents to control Android devices.

Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.

MCP Server for AI-driven BlazeMeter performance testing

Cyber Host Artificial Intelligence (C.H.A.I) is Autonomous penetration testing MCP (Model Context Protocol) server with an integrated AI decision engine, multi-provider LLM support, and an extensible plugin architecture.

MCP server for email compatibility analysis. Analyze, preview, diff, and fix HTML emails across 15 email clients — plus capture real screenshots and create shareable links with an optional API key.

This tool creates an MCP server to bridge the gap between AI workflows and EMBA security analysis.

High-performance mobile automation architecture with a thin MCP gateway and dedicated Go workers for Android and iOS.

Security MCP server that turns your AI into a penetration tester.

A Python MCP Server that connects Large Language Models natively to a comprehensive suite of offensive security tools.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.