# Puppeteer

> Use this tool when you need to automate web browsing, scrape data, or perform automated testing, as it provides a standardized interface for browser automation, supporting features like screenshot capture, form filling, and JavaScript execution. It accepts inputs such as URLs, JavaScript code, and form data, and outputs screenshots, extracted data, and execution results. Ideal for AI-assisted web browsing, web scraping, and automated testing scenarios, this tool enables flexible and reliable web interaction.

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

## Description

This Puppeteer MCP server, developed by Anthropic, provides browser automation capabilities through a standardized interface. Built with TypeScript and leveraging Puppeteer, it offers tools for web navigation, interaction, and data extraction. The implementation supports both new browser instances and connections to existing Chrome windows, enabling flexible deployment scenarios. It includes features like screenshot capture, form filling, and JavaScript execution, making it suitable for web scraping, automated testing, and AI-assisted web browsing. The server's logging system and error handling enhance its reliability and debuggability. By bridging AI models with web automation, this implementation enables sophisticated web interaction scenarios, particularly useful for AI assistants or applications requiring programmatic web access.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-02

## Source

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

## 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": "merajmehrabi-puppeteer"
    }
  }
}
```

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