# Windows Screenshots

> Use this tool when you need to access and analyze Windows screenshots from WSL2 environments, solving problems of manual file path navigation and enabling AI workflows to reference screenshots programmatically. It takes environment variables and directory configurations as inputs and provides outputs such as recent screenshot metadata, specific screenshot paths, and base64 content. Use it in contexts where automated screenshot analysis or reference is required, such as AI-powered testing or content creation workflows.

Canonical page: https://skillsregistry.net/skills/rubinsh-windows-screenshots  
JSON: https://api.skillsregistry.net/v1/skills/rubinsh-windows-screenshots

## Description

This MCP server enables AI assistants to access Windows screenshots from WSL2 environments by automatically detecting common screenshot directories and providing three specialized tools for listing recent screenshots with metadata, retrieving specific screenshot paths or base64 content, and showing configured directories. Built by rubinsh using TypeScript with the Model Context Protocol SDK, it features smart directory detection for OneDrive and custom paths, environment variable configuration for Windows username and custom directories, semicolon-separated multiple directory support, and file pattern filtering for common image formats. The implementation eliminates manual file path navigation by providing programmatic access to Windows screenshot locations from within WSL2, making it valuable for AI workflows that need to analyze or reference screenshots without requiring users to manually locate and specify file paths.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rubinsh-windows-screenshots)
- **Repository:** <https://github.com/rubinsh/mcp-windows-screenshots>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rubinsh-windows-screenshots"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rubinsh-windows-screenshots` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rubinsh-windows-screenshots/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt