mcp-windows-screenshots: Instructions file for Claude Code

CLAUDE.md

mcp-windows-screenshots CLAUDE.md is an instructions file for Claude Code from rubinsh/mcp-windows-screenshots. It costs 527 tokens per session, scanned A, original, MIT.

A project guide for an MCP server that lets Claude access screenshots stored in Windows folders from WSL2, the Linux environment that runs alongside Windows. It documents the server's commands, build process, and available tools.

In plain words
What is it for?
Use it to list recent screenshots and their metadata, retrieve a selected screenshot by path or image data, view configured screenshot directories, build the TypeScript source, and run the server locally.
Why use it?
It removes the need to manually find and copy Windows screenshot paths into the assistant. It also gives developers a repeatable way to build, run, and connect the server while testing changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rubinsh/mcp-windows-screenshots's own configuration. It tells Claude Code how to work on mcp-windows-screenshots itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-windows-screenshots configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rubinsh/mcp-windows-screenshots. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rubinsh/mcp-windows-screenshots/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rubinsh/mcp-windows-screenshots

Made for: Claude Code.

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 mcp-windows-screenshots CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rubinsh/mcp-windows-screenshots/claude-md/github.svg)](https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md"><img src="https://agentmods.dev/badge/instructions/rubinsh/mcp-windows-screenshots/claude-md/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 mcp-windows-screenshots CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md"><img src="https://agentmods.dev/badge/instructions/rubinsh/mcp-windows-screenshots/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 527 This file is loaded in full into every session.
When invoked 527 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 $0.00527 $0.00527
Opus 5 $0.00264 $0.00264
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00053 $0.00053

Measured 9d ago against content hash c682c51c0d53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-windows-screenshots CLAUDE.md 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 9d 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.

CLAUDE.md · 66 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) server that enables Claude to access Windows screenshots from WSL2 environments. It's designed to simplify screenshot sharing by eliminating the need for manual file path navigation.

Development Commands

# Install dependencies
npm install

# Build TypeScript to JavaScript
npm run build

# Development mode with auto-rebuild
npm run dev

# Test the server locally
node dist/index.js

MCP Server Architecture

  • Transport: stdio-based communication
  • Tools Provided:
    • list_screenshots: Lists recent screenshots with metadata
    • get_screenshot: Retrieves a specific screenshot (path or base64 content)
    • list_directories: Shows all configured screenshot directories
  • Entry Points:
    • cli.js: NPX entry point that spawns the server
    • src/index.ts: Main server implementation

Testing the MCP Server

To test changes locally before publishing:

# Build and test with Claude Code
npm run build
claude mcp add windows-screenshots-dev node /path/to/project/dist/index.js

# Remember to remove test server after testing
claude mcp remove windows-screenshots-dev

Publishing to NPM

# Bump version in package.json
npm version patch  # or minor/major

# Publish (build runs automatically via prepublishOnly)
npm publish

# Test the published version
npx mcp-windows-screenshots@latest

Common Development Tasks

  • Adding new screenshot directories: Modify getScreenshotDirectories() in src/index.ts
  • Changing file patterns: Update the glob patterns in list_screenshots tool
  • Adding new MCP tools: Follow the pattern in server.setRequestHandler()
  • Debugging MCP communication: Errors go to stderr, use console.error() for debugging

Important Notes

  • This is an MCP server meant to be installed via claude mcp add command
  • Users install it with: claude mcp add windows-screenshots -- npx mcp-windows-screenshots@latest
  • Environment variables (WINDOWS_USERNAME, MCP_SCREENSHOT_DIRS) are passed via -e flags during installation
  • The server runs as a subprocess of Claude Code and communicates via stdio
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. 9d ago First seen · 66 lines · 527 tokens per session scan A c682c51c0d53

Subscribe to this mod's changes

mcp-windows-screenshots CLAUDE.md is an instructions file published in the GitHub repository rubinsh/mcp-windows-screenshots (6 stars, last pushed 1y ago), licensed MIT. It adds 527 tokens to every session, about $0.0026 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens