# Puppeteer

> Use this tool when you need to automate web browser interactions, perform visual AI tasks, or debug web applications. It provides a powerful interface for language models to interact with web browsers, enabling tasks such as navigation, form filling, and JavaScript execution. Ideal for use cases like AI-driven web testing, data scraping, and automated web interactions, it offers screenshot capabilities and console log monitoring for high-fidelity web interactions.

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

## Description

This Puppeteer-based MCP implementation provides a powerful interface for language models to interact with web browsers. Developed by Anthropic, it enables AI agents to perform a wide range of browser automation tasks including navigation, clicking, form filling, and JavaScript execution in real browser environments. The implementation distinguishes itself by offering screenshot capabilities and console log monitoring, making it ideal for visual AI tasks and debugging. By leveraging Puppeteer's Chrome/Chromium automation, it ensures high-fidelity web interactions. This tool is particularly powerful for AI-driven web testing, data scraping, and automated web interactions, enabling more sophisticated AI assistants that can directly manipulate web applications. Its integration with Claude Desktop and npm-based installation process make it easily accessible for developers and researchers working on advanced AI projects involving web automation.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-02

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/modelcontextprotocol-puppeteer)
- **Repository:** <https://github.com/modelcontextprotocol/servers-archived/tree/HEAD/src/puppeteer>

## 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": "modelcontextprotocol-puppeteer"
    }
  }
}
```

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