Hyperbrowser Model Context Protocol (MCP) server for cloud headless browser automation, dynamic SPA crawling, session recording, and stealth web scraping (hyperbrowserai/mcp). Use when the agent needs to render complex JavaScript single-page apps, crawl websites, or execute browser agents.
Installs into .claude/skills of the current project.
Are you the author of Hyperbrowser Mcp?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/smartworldarafath-hyperbrowser-mcp)
---
name: hyperbrowser-mcp
description: Hyperbrowser Model Context Protocol (MCP) server for cloud headless browser automation, dynamic SPA crawling, session recording, and stealth web scraping (hyperbrowserai/mcp). Use when the agent needs to render complex JavaScript single-page apps, crawl websites, or execute browser agents.
---
# Hyperbrowser MCP (Cloud Headless Browser Automation & Crawling)
Based on [hyperbrowserai/mcp](https://github.com/hyperbrowserai/mcp): an MCP server providing cloud headless browser automation, dynamic JavaScript rendering, full-site crawling, and structured web data extraction for AI agents.
---
## 🎯 When to Use
- **Complex Single-Page Applications (SPAs):** Scraping websites that rely on heavy client-side JavaScript, React/Vue hydration, or WebGL where static HTML extractors return blank templates.
- **Deep Site Crawling:** Recursively following links across web applications, documentation trees, or API portals.
- **Stealth Browsing & Session Recordings:** Recording video replays and interaction traces of web navigation for verification and audit trails.
- **Browser Agent Delegation:** Powering browser agents (such as Claude Computer Use, OpenAI CUA, or Browser Use).
---
## 🚀 Setup & Registration
### MCP Configuration
Register Hyperbrowser MCP in your agent's configuration (`.mcp.json` or IDE settings):
```json
{
"mcpServers": {
"hyperbrowser": {
"command": "npx",
"args": ["-y", "hyperbrowser-mcp"],
"env": {
"HYPERBROWSER_API_KEY": "YOUR_HYPERBROWSER_API_KEY"
}
}
}
}
```
---
## 🛠️ Key Capabilities & Tools
- `crawl_page`: Crawls dynamic web applications and returns fully rendered DOM contents and structured link trees.
- `extract_data`: Uses vision and LLM parsing to turn visual elements on web pages into clean JSON data models.
- `record_session`: Records full interactive browser sessions into shareable artifacts for test reports and audits.
---
## ⚡ Integration with REA & Security Audits
- **Auditing Client-Side Rendered Applications:** Render Next.js, Nuxt, or Vite web apps in Hyperbrowser to intercept WebSocket connections, runtime-injected scripts, and dynamic API calls that do not appear in raw HTML.
- **Visual Regression Verification:** Capture live renders of web applications after applying security headers or CSP rules to confirm user interface integrity.