Loading connector details…
Hyperbrowser MCP Server
MCPOfficialOpen SourceMIT74.3
by hyperbrowserai • Search & Retrieval
An MCP server that provides web scraping, crawling, structured-data extraction, and browser automation agents (OpenAI CUA, Claude, Browser Use) for agents requiring web interaction.
Example Use Cases
- 1
Extract readable, LLM-friendly content (markdown, screenshots, text) from arbitrary webpages for summarization or answering queries.
- 2
Crawl a set of linked pages and produce structured, consolidated content or datasets for downstream analysis or knowledge ingestion.
- 3
Programmatic browser automation (form submission, navigation, screenshots) or to run complex tasks using OpenAI CUA or Claude Computer Use agents.
Description
Hyperbrowser MCP Server exposes tools to scrape and format webpages, crawl linked pages, convert HTML to structured JSON, perform Bing searches, and run lightweight or advanced browser automation via multiple agents (OpenAI CUA, Claude Computer Use, Browser Use). It integrates with MCP-capable clients (examples: Claude Desktop, Cursor, Windsurf) and supports persistent profiles for automated workflows. The server also publishes resource documentation for client discovery and can be run locally or via npx for easy deployment.
Capabilities(64 total)
Tools (10)
scrape_webpage
Scrape a webpage and extract its content in various formats. This tool allows fetching content from a single URL with configurable browser behavior options. Use this for extracting text content, HTML structure, collecting links, or capturing screenshots of webpages.
url:string*sessionOptions:objectoutputFormat:array*
crawl_webpages
Crawl a website starting from a URL and explore linked pages. This tool allows systematic collection of content from multiple pages within a domain. Use this for larger data collection tasks, content indexing, or site mapping.
url:string*sessionOptions:objectoutputFormat:array*followLinks:boolean*maxPages:integerignoreSitemap:boolean
extract_structured_data
Extract structured data from a webpage. This tool allows you to extract structured data from a webpage using a schema.
urls:array*prompt:string*schema:anysessionOptions:object
browser_use_agent
This tool employs an open-source browser automation agent optimized specifically for fast, efficient, and cost-effective browser tasks using a cloud browser. It requires explicit, detailed instructions to perform highly specific interactions quickly. Optimal for tasks requiring: - Precise, explicitly defined interactions and actions - Speed and efficiency with clear, unambiguous instructions - Cost-effective automation at scale with straightforward workflows Best suited use cases include: - Explicitly defined registration and login processes - Clearly guided navigation through web apps - Structured, step-by-step web scraping with detailed guidance - Extracting data via explicitly specified browser interactions You must provide extremely detailed step-by-step instructions, including exact elements, actions, and explicit context. Clearly define the desired outcome for optimal results. Returns the completed result or an error message if issues arise. Note: This agent trades off flexibility for significantly faster performance and lower costs compared to Claude and OpenAI agents.
task:string*sessionOptions:objectreturnStepInfo:booleanmaxSteps:integer
openai_computer_use_agent
This tool utilizes OpenAI's model to autonomously execute general-purpose browser-based tasks with balanced performance and reliability using a cloud browser. It handles complex interactions effectively with practical reasoning and clear execution. Optimal for tasks requiring: - Reliable, general-purpose browser automation - Clear, structured interactions with moderate complexity - Efficient handling of common web tasks and workflows Best suited use cases include: - Standard multi-step registration or form submissions - Navigating typical web applications requiring multiple interactions - Conducting structured web research tasks - Extracting data through interactive web processes Provide a clear step-by-step description, necessary context, and expected outcomes. Returns the completed result or an error message if issues arise.
task:string*sessionOptions:objectreturnStepInfo:booleanmaxSteps:integer
Resources (54)
Welcome to Hyperbrowser | Hyperbrowser
Hyperbrowser documentation provides an introduction to web scraping and automation using the Hyperbrowser tool.
URI: hyperbrowser:///MIME: text/markdown
What are Headless browsers ? | Hyperbrowser
The page explains headless browsers and their role in Hyperbrowser for web scraping and automation tasks.
URI: hyperbrowser:///what-are-headless-browsersMIME: text/markdown
Scraping | Hyperbrowser
The "Scraping" page in Hyperbrowser details how to extract data from websites using the tool's functionalities.
URI: hyperbrowser:///get-started/quickstart/scrapingMIME: text/markdown
Crawling | Hyperbrowser
The "Crawling" page of Hyperbrowser covers the tool's web scraping capabilities and how to implement them.
URI: hyperbrowser:///get-started/quickstart/crawlingMIME: text/markdown
Quickstart | Hyperbrowser
Quickstart guide for Hyperbrowser provides initial setup and functionality instructions for effective web scraping and automation.
URI: hyperbrowser:///get-started/quickstartMIME: text/markdown
Quick Actions
Security
Scanned 3 month(s) agoRisk Level
MINIMAL
Read-only data retrieval, no side effects
Trust Score
C52/100
4/17 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 ModelUnknown
Capabilities10 Tools / 0 Prompts / 54 Resources
Ownerhyperbrowserai
CategorySearch & Retrieval
DependenciesStandalone
Tags
Web scrapingContent extractionCrawlingBrowser automation