Puppeteer Browser Automation

MCPOpen Source10.0

by hieu-blackbox • Analytics & Monitoring

A Model Context Protocol (MCP) server that lets LLMs automate and interact with real browser sessions using Puppeteer for navigation, screenshots, and JS execution.

Example Use Cases

1
Navigate and interact with live web pages (click, hover, fill forms, select options) to gather dynamic content or perform tasks that require a real browser.
2
Capture visual context or evidence via full-page or element-level screenshots for reports, QA, or documentation.
3
Execute and evaluate JavaScript in-page and collect browser console logs for debugging, scraping dynamic data, or validating client-side behavior.

Description

This MCP server exposes Puppeteer-driven browser automation capabilities (navigation, clicking, hovering, form filling, selecting, executing JS) to agents via standardized tools and resources. It also captures browser console logs and screenshots as resources accessible to agents. Deployment options include Docker (headless Chromium) and NPX (launches a visible browser), and the project is MIT licensed for free use and modification. Useful for testing, scraping, visual capture, and any agent needing real-browser context.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D40/100

3/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerhieu-blackbox

CategoryAnalytics & Monitoring

DependenciesStandalone