What is mcp-screenshot-server CLAUDE.md?

Repository instructions for an MCP server that gives AI assistants tools to capture web-page and computer-screen screenshots. MCP is a standard way for software tools to connect to AI assistants.

Use them when developing or testing the screenshot server, including its browser-based, operating-system, integration, and end-to-end tests.

They explain how the project is structured, configured, built, tested, and debugged, so contributors know how to work on it.

How sethbang/mcp-screenshot-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sethbang/mcp-screenshot-server. 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/sethbang/mcp-screenshot-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sethbang/mcp-screenshot-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sethbang/mcp-screenshot-server/claude-md/github.svg)](https://agentmods.dev/instructions/sethbang/mcp-screenshot-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sethbang/mcp-screenshot-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sethbang/mcp-screenshot-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sethbang/mcp-screenshot-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sethbang/mcp-screenshot-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,342 This file is loaded in full into every session.

When invoked 1,342 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.

Model	Per session	Once invoked
Fable 5.1	$0.01342	$0.01342
Opus 5.5	$0.00537	$0.00537
Sonnet 5.5	$0.00268	$0.00268
Haiku 4.5	$0.00134	$0.00134

Measured 9d ago against content hash 3232e339a075, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-screenshot-server 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

What This Is

An MCP (Model Context Protocol) server that provides two screenshot tools to AI assistants:

take_screenshot — web page capture via headless Puppeteer/Chromium
take_system_screenshot — cross-platform system screenshots using native OS tools (macOS screencapture, Linux maim/scrot/etc., Windows PowerShell+.NET)

Published to npm as universal-screenshot-mcp.

Commands

npm run build            # TypeScript → build/ (also runs on npm install via "prepare")
npm run watch            # Recompile on change
npm test                 # Unit tests only (fast, fully mocked)
npm run test:integration # Integration tests (real DNS, real filesystem)
npm run test:e2e         # E2E tests (real Puppeteer, real screencapture; run `npm run build` first)
npm run test:all         # All tiers together
npm run test:linux       # Linux e2e via Docker (Xvfb + maim/scrot/import)
npm run test:watch       # Watch mode
npm run test:coverage    # With coverage
npm run lint             # ESLint on src/
npm run inspector        # Launch MCP Inspector for interactive tool debugging

Run a single test file: npx vitest run tests/validators/url.test.ts

Environment Variables

ALLOW_LOCAL=true — Permit loopback addresses (127.x.x.x, ::1, localhost) through SSRF validation. Useful for screenshotting local dev servers. Off by default.
SCREENSHOT_OUTPUT_DIR — Override the default screenshot output directory (relative to ~). Defaults to ~/Documents/screenshots.

Architecture

ESM-only ("type": "module"), TypeScript strict mode, target ES2022, Node16 module resolution. Output goes to build/.

Entry flow

src/index.ts → passes a createServer factory (from src/server.ts) to serveStdio(). server.ts registers both tools on an McpServer instance.

serveStdio() owns the protocol-era decision: the opening exchange selects the era and pins one server instance for the connection's lifetime. Its legacy option is deliberately left at the default 'serve' so clients still speaking the 2025-era initialize handshake keep working — passing 'reject' would break every currently-installed client.

Read the full file on GitHub · 86 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.

9d ago Changed · +4 lines · +120 tokens per session 3232e339a075
2mo ago First seen · 82 lines · 1,222 tokens per session scan A a97ab64bd04f

Subscribe to this mod's changes

mcp-screenshot-server CLAUDE.md is an instructions file published in the GitHub repository sethbang/mcp-screenshot-server (37 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,342 tokens to every session, about $0.0054 per session on Opus 5.5. 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 2026-08-30.

ai ai-agents linux macos mcp mcp-server

mcp-screenshot-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-screenshot-server CLAUDE.mdsethbang/mcp-screenshot-server	Instructions file	37	10d ago	Apache-2.0	A	1,342	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

mcp-screenshot-server: Instructions file for Claude Code