# Puppeteer

> Use this tool when you need to capture full-page screenshots of web pages at multiple viewport breakpoints with error monitoring and optimization features. It solves problems related to responsive design testing, automated visual testing, and page health monitoring, accepting webpage URLs as input and producing screenshots in PNG or JPEG formats with rich metadata as output. Ideal for web developers, QA teams, and designers, it provides a single tool for handling various screen widths and image formats with quality controls and optimization features.

Canonical page: https://skillsregistry.net/skills/hushaudio-puppeteer  
JSON: https://api.skillsregistry.net/v1/skills/hushaudio-puppeteer

## Description

This MCP server provides web screenshot capabilities using Puppeteer, enabling AI assistants to capture full-page screenshots at multiple viewport breakpoints (mobile, tablet, desktop) with comprehensive error monitoring and optimization features. Built with TypeScript and the MCP SDK, it offers a single screenshot tool that handles responsive design testing by automatically capturing images at different screen widths, includes detailed page error collection (JavaScript errors, console messages, network failures, CORS issues), supports both PNG and JPEG formats with quality controls, implements image optimization through width clipping for large viewports, and provides rich metadata including load times, actual content dimensions, and error summaries. The implementation features browser instance reuse for performance, configurable wait conditions for dynamic content, and detailed error reporting with categorization by type and severity level, making it valuable for web developers, QA teams, and designers who need automated visual testing, responsive design validation, and comprehensive page health monitoring through AI-assisted workflows.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/hushaudio-puppeteer)
- **Repository:** <https://github.com/hushaudio/puppeteermcp>

## 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": "hushaudio-puppeteer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hushaudio-puppeteer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hushaudio-puppeteer/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