Hyperbrowser
Free新一代 AI 代理浏览器自动化平台，支持大规模、无缝操作。
FreeFree tier
Inputs: url
About Hyperbrowser
Hyperbrowser MCP Server is an open-source Model Context Protocol (MCP) server that provides a set of tools for web scraping, crawling, structured data extraction, and browser automation. It integrates with Hyperbrowser's API to enable AI agents to interact with web pages, extract LLM-friendly content, and automate browser tasks using agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use. The server supports persistent browser profiles and can be easily installed via npx or configured with Claude Desktop, Cursor, and Windsurf. Licensed under MIT.
Key Features
Scrape webpages and extract content in markdown or screenshot format
Crawl multiple linked pages and extract LLM-friendly formatted data
Extract structured data (JSON) from messy HTML
Search the web using Bing integration
General-purpose browser automation with Browser Use agent
Automation using OpenAI's CUA model (computer use agent)
Complex browser tasks using Anthropic's Claude Computer Use agent
Create, delete, and list persistent Hyperbrowser profiles
Open source (MIT license)
Easy installation via npx or Docker
Pros & Cons
Pros
- Free and open source (MIT license)
- Supports multiple browser automation agents (CUA, Claude, Browser Use)
- Easy setup with npx and integration with Claude Desktop, Cursor, Windsurf
- Provides both scraping and structured data extraction
- Persistent browser profiles for maintaining sessions
- Active development on GitHub with community support
Cons
- Requires a Hyperbrowser API key for full functionality
- Limited to the Hyperbrowser ecosystem for advanced features
- Bing search tool may be less flexible than other search APIs
- Documentation primarily in English; limited non-English resources
Best For
Web scraping and data extraction for AI/ML pipelinesAutomated browser testing and UI interactionSearch and retrieve web content for LLM contextStructured data collection from multiple pagesPersistent session management for web automation
FAQ
What is Hyperbrowser MCP Server?
It is an open-source server implementing the Model Context Protocol (MCP) that provides tools for web scraping, crawling, structured data extraction, and browser automation using AI agents.
How do I install Hyperbrowser MCP Server?
You can install it via npx: `npx hyperbrowser-mcp YOUR-HYPERBROWSER-API-KEY`. Alternatively, you can clone the repository and build from source, or use Docker.
What tools are available?
Tools include: scrape_webpage, crawl_webpages, extract_structured_data, search_with_bing, browser_use_agent, openai_computer_use_agent, claude_computer_use_agent, create_profile, delete_profile, and list_profiles.
Is Hyperbrowser MCP Server free?
Yes, the server is open source under the MIT license and free to use. However, using it requires a Hyperbrowser API key, which may have its own pricing.
Can I use it with Claude Desktop?
Yes, you can configure it as an MCP server in Claude Desktop by adding the appropriate configuration to your Claude config file.