mcp  by hyperbrowserai

MCP server for Hyperbrowser

Created 10 months ago
703 stars

Top 48.6% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a Model Context Protocol (MCP) server implementation for Hyperbrowser, enabling web scraping, structured data extraction, and crawling. It offers easy integration with general-purpose browser agents like OpenAI's CUA and Anthropic's Claude, targeting developers and researchers who need to automate web data acquisition and processing for LLM applications.

How It Works

The MCP server acts as a bridge between LLM agents and web browsing capabilities. It leverages Node.js and npx for installation and execution, allowing clients to invoke specific tools for web interaction. These tools include webpage scraping (Markdown, screenshots), multi-page crawling, HTML-to-JSON conversion, and web search via Bing, all managed through a defined protocol.

Quick Start & Requirements

  • Primary install/run command: npx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>
  • Prerequisites: Node.js, npx, a Hyperbrowser API key.
  • Installation via Smithery: npx -y @smithery/cli install @hyperbrowserai/mcp --client claude
  • Development setup: git clone, npm install (or yarn install), npm run build, node dist/server.js.
  • Documentation: hyperbrowser API, Model Context Protocol

Highlighted Details

  • Supports multiple browser agents: OpenAI CUA, Anthropic Claude Computer Use.
  • Offers tools for structured data extraction from messy HTML.
  • Enables persistent profile management (create, delete, list).
  • Integrates with clients like Cursor and Windsurf via configuration files.

Maintenance & Community

The project is hosted on GitHub by hyperbrowserai. No specific community channels or roadmap details are provided in the README.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Permissive MIT license allows for commercial use and integration with closed-source applications.

Limitations & Caveats

The README mentions that the hyperbrowser API supports a superset of features present in the MCP server, implying the server might not expose all Hyperbrowser functionalities. A Hyperbrowser API key is required for operation.

Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
2
Issues (30d)
0
Star History
54 stars in the last 30 days

Explore Similar Projects

Starred by Tobi Lutke Tobi Lutke(Cofounder of Shopify), Dirk Englund Dirk Englund(MIT EECS Professor and Cofounder of Axiomatic AI), and
25 more.

firecrawl by firecrawl

1.8%
74k
API service for turning websites into LLM-ready data
Created 1 year ago
Updated 2 days ago
Feedback? Help us improve.