GitHub - hyperbrowserai/mcp: A MCP server implementation for hyperbrowser

The Hyperbrowser MCP Server is a tool designed to facilitate web scraping, data extraction, and webpage crawling. It offers access to various browser agents, including OpenAI's CUA and Anthropic's Claude Computer Use, to automate tasks efficiently. The server can be installed using the command `npx hyperbrowser-mcp `, and it supports integration with platforms like Cursor and Windsurf through specific configuration files. For development, users can clone the repository, install dependencies, and build the server from source code.

The server provides several tools, such as `scrape_webpage` for extracting formatted content, `crawl_webpages` for navigating linked pages, and `extract_structured_data` for converting HTML to JSON. It also includes agents for browser automation and web search. The Hyperbrowser MCP Server is documented through its resources methods, allowing clients to access detailed information. The project is open-source and licensed under the MIT License.

Key takeaways

Hyperbrowser MCP Server provides tools for scraping, extracting structured data, and crawling webpages.
It supports browser agents like OpenAI's CUA and Anthropic's Claude Computer Use.
Installation involves running a command with your Hyperbrowser API key.
The project is licensed under the MIT License.

GitHub - hyperbrowserai/mcp: A MCP server implementation for hyperbrowser

Key takeaways

Discussion (0)