project-description

project-description is a cursor rule for Cursor from Tiartyos/mcp-window-screenshooter. It costs 961 tokens per session, scanned A, original, MIT.

An MCP server that lets an AI agent capture a screenshot of a selected application window. MCP is a standard way for tools to communicate with AI agents.

In plain words
What is it for?
Use it for window-specific screenshots on Windows, Linux, or macOS, especially during automated testing, visual checks, and application monitoring.
Why use it?
It captures only the relevant window instead of the entire desktop, which is useful when checking or monitoring an application.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it for window-specific screenshots on Windows, Linux, or macOS, especially during automated testing, visual checks, and application monitoring.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/tiartyos/mcp-window-screenshooter/project-description
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Tiartyos/mcp-window-screenshooter

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for project-description

README.md
[![agentmods](https://agentmods.dev/badge/rules/tiartyos/mcp-window-screenshooter/project-description/github.svg)](https://agentmods.dev/rules/tiartyos/mcp-window-screenshooter/project-description)
Your own site
<a href="https://agentmods.dev/rules/tiartyos/mcp-window-screenshooter/project-description"><img src="https://agentmods.dev/badge/rules/tiartyos/mcp-window-screenshooter/project-description/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-description

Your own site · 80×15
<a href="https://agentmods.dev/rules/tiartyos/mcp-window-screenshooter/project-description"><img src="https://agentmods.dev/badge/rules/tiartyos/mcp-window-screenshooter/project-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 961 This file is loaded in full into every session.
When invoked 961 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00961 $0.00961
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 8d ago against content hash 754c114918ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-description scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/project-description.mdc · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Window Screenshooter MCP Server A cross-platform Model Context Protocol (MCP) server that enables AI agents to capture screenshots of specific application windows, kupo!

Overview Window Screenshooter is an MCP server built in Python that provides AI agents with the capability to take targeted screenshots of specific application windows across Windows, Linux, and macOS platforms. Unlike traditional screen capture solutions that only capture the entire screen, this server allows precise window-based capture for AI verification workflows, automated testing, and application monitoring.

Key Features:

🖼️ Window-Specific Capture: Target individual application windows by name or title

🌐 Cross-Platform Support: Works on Windows, Linux, and macOS with platform-optimized backends

🔧 MCP Integration: Seamless integration with AI agents through Model Context Protocol

📡 STDIO Transport: Uses standard input/output for reliable communication

⚡ Performance Optimized: Platform-specific implementations for maximum efficiency

Technical Architecture Cross-Platform Window Management Built on PyWinCtl, a robust cross-platform library that evolved from PyGetWindow to support:

Window enumeration and identification across all platforms

Multi-monitor setup compatibility

Window state management and control

Platform-Specific Capture Backends Windows Implementation:

Utilizes win32gui with BitBlt API for robust window capture

Can capture minimized, hidden, or overlapped windows

High-performance Graphics Capture API integration option

Linux Implementation:

Xlib-based window capture using native X11 protocols

Direct window buffer access for efficient capture

Support for Wayland environments where available

macOS Implementation:

Coordinate-based capture with PyWinCtl window positioning

Native macOS window server integration

Optimized for Retina displays

MCP Tool Integration The server exposes the following MCP tools:

capture_window Captures a screenshot of a specific window by title or identifier.

Parameters:

window_title (string): Exact or partial window title to match

output_path (string, optional): Save location for screenshot

format (string, optional): Image format (PNG, JPEG)

quality (int, optional): JPEG quality (1-100)

Returns: Base64-encoded image data or file path confirmation

list_windows Enumerates all available windows on the system.

Returns: Array of window objects with ID, title, position, and size information

get_window_info Retrieves detailed information about a specific window.

Parameters:

window_identifier (string): Window title or ID

Returns: Window metadata including position, size, visibility state, and process information

Use Cases AI Development Workflows:

Code Verification: AI takes Unity editor screenshots to verify game object placement

UI Testing: Capture application states during automated testing sequences

Documentation: Generate visual documentation of application interfaces

Debugging: Visual confirmation of application behavior changes

Automation Scenarios:

Quality Assurance: Screenshot comparison for regression testing

Process Monitoring: Capture application states for workflow verification

Training Data: Generate labeled screenshots for computer vision training

Installation & Setup bash

Clone the MCP server template

git clone https://github.com/sontallive/mcp-server-python-template cd mcp-server-python-template

Read the full file on GitHub · 187 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 187 lines · 961 tokens per session scan A 754c114918ee

Subscribe to this mod's changes

project-description is a cursor rule published in the GitHub repository Tiartyos/mcp-window-screenshooter (0 stars, last pushed 1y ago), licensed MIT. It adds 961 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.