Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation.
Detailed security scan evidence is not public for this MCP yet. Public identity, registry metadata, and independently observed protocol inventory remain available.
Installation and connection instructions are shown only when supported by retained package, repository, or endpoint evidence.
Version 1.0.25 declares 1 executable entrypoint.
npm install --save-exact hyperbrowser-mcp@1.0.25npx -y -p hyperbrowser-mcp@1.0.25 hyperbrowser-mcp{
"mcpServers": {
"hyperbrowser-mcp": {
"command": "npx",
"args": [
"-y",
"-p",
"hyperbrowser-mcp@1.0.25",
"hyperbrowser-mcp"
]
}
}
}| Canonical slug | hyperbrowser-98813a5b | Deployment | Local Only |
|---|---|---|---|
| Canonical package | npm:hyperbrowser-mcp | Repository | hyperbrowserai/mcp |
| First published | — | Latest release | — |
| Last security verification | — | Classification confidence | 90% |
| Publication | Draft | Official distribution | Not verified |
| Channel | Identifier | Current version | Versions | Source |
|---|---|---|---|---|
| npm | hyperbrowser-mcp | 1.0.25 | 26 | Repository |
| Package | Version | Published / observed | Inventory | Security scan |
|---|---|---|---|---|
| npmhyperbrowser-mcp | 1.0.25Current | Sep 5, 2026 | 10 toolsPartial · 54 resources · 0 prompts | Evidence restricted |
Independently scan the exact version your agents use, receive alerts when its risk changes, and investigate every finding with retained version evidence.
No public current-version evidence is available yet.
| Tool | Category | Annotations | Risk |
|---|---|---|---|
browser_use_agentThis 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.Input schema{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The task to perform inside the browser"
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"returnStepInfo": {
"type": "boolean",
"default": false,
"description": "Whether to return step-by-step information about the task.Should be false by default. May contain excessive information, so we strongly recommend setting this to false."
},
"maxSteps": {
"type": "integer",
"exclusiveMinimum": 0,
"minimum": 1,
"maximum": 100,
"default": 25
}
},
"required": [
"task"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
claude_computer_use_agentThis tool leverages Anthropic's Claude model to autonomously execute complex browser tasks with sophisticated reasoning capabilities using a cloud browser. It specializes in handling intricate, nuanced, or highly context-sensitive web interactions.
Optimal for tasks requiring:
- Complex reasoning over multiple web pages
- Nuanced interpretation and flexible decision-making
- Human-like interaction with detailed context awareness
Best suited use cases include:
- Multi-step processes requiring reasoning (e.g., detailed registrations or onboarding)
- Interacting intelligently with advanced web apps
- Conducting in-depth research with complex conditions
- Extracting information from dynamic or interactive websites
Provide detailed task instructions, relevant context, and clearly specify the desired outcome for best results. Returns the completed result or an error message if issues arise.Input schema{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The task to perform inside the browser"
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"returnStepInfo": {
"type": "boolean",
"default": false,
"description": "Whether to return step-by-step information about the task.Should be false by default. May contain excessive information, so we strongly recommend setting this to false."
},
"maxSteps": {
"type": "integer",
"exclusiveMinimum": 0,
"minimum": 1,
"maximum": 100,
"default": 25
}
},
"required": [
"task"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
crawl_webpagesCrawl 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.Input schema{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The URL of the webpage to crawl."
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"outputFormat": {
"type": "array",
"items": {
"type": "string",
"enum": [
"markdown",
"html",
"links",
"screenshot"
]
},
"minItems": 1,
"description": "The format of the output"
},
"followLinks": {
"type": "boolean",
"description": "Whether to follow links on the crawled webpages"
},
"maxPages": {
"type": "integer",
"exclusiveMinimum": 0,
"minimum": 1,
"maximum": 100,
"default": 10
},
"ignoreSitemap": {
"type": "boolean",
"default": false
}
},
"required": [
"url",
"outputFormat",
"followLinks"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
create_profileCreates a new persistent Hyperbrowser profile.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {}
} | — | — | |
delete_profileDeletes an existing persistent Hyperbrowser profile.Input schema{
"type": "object",
"properties": {
"profileId": {
"type": "string",
"description": "ID of the profile to delete"
}
},
"required": [
"profileId"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
extract_structured_dataExtract structured data from a webpage. This tool allows you to extract structured data from a webpage using a schema.Input schema{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"description": "The list of URLs of the webpages to extract structured information from. Can include wildcards (e.g. https://example.com/*)"
},
"prompt": {
"type": "string",
"description": "The prompt to use for the extraction"
},
"schema": {
"description": "The json schema to use for the extraction. Must provide an object describing a spec compliant json schema, any other types are invalid."
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
}
},
"required": [
"urls",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
list_profilesLists existing persistent Hyperbrowser profiles, with optional pagination.Input schema{
"type": "object",
"properties": {
"page": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Page number for pagination (optional)"
},
"limit": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Number of profiles per page (optional)"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
openai_computer_use_agentThis 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.Input schema{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The task to perform inside the browser"
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"returnStepInfo": {
"type": "boolean",
"default": false,
"description": "Whether to return step-by-step information about the task.Should be false by default. May contain excessive information, so we strongly recommend setting this to false."
},
"maxSteps": {
"type": "integer",
"exclusiveMinimum": 0,
"minimum": 1,
"maximum": 100,
"default": 25
}
},
"required": [
"task"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
scrape_webpageScrape 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.Input schema{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The URL of the webpage to scrape"
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"outputFormat": {
"type": "array",
"items": {
"type": "string",
"enum": [
"markdown",
"html",
"links",
"screenshot"
]
},
"minItems": 1,
"description": "The format of the output"
}
},
"required": [
"url",
"outputFormat"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
search_with_bingSearch the web using Bing. This tool allows you to search the web using bing.comInput schema{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query to submit to Bing"
},
"sessionOptions": {
"type": "object",
"properties": {
"useProxy": {
"type": "boolean",
"default": false,
"description": "Whether to use a proxy. Recommended false."
},
"useStealth": {
"type": "boolean",
"default": false,
"description": "Whether to use stealth mode. Recommended false."
},
"solveCaptchas": {
"type": "boolean",
"default": false,
"description": "Whether to solve captchas. Recommended false."
},
"acceptCookies": {
"type": "boolean",
"default": false,
"description": "Whether to automatically close the accept cookies popup. Recommended false."
},
"profile": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the persistent profile to use for the session"
},
"persistChanges": {
"type": "boolean",
"default": true,
"description": "Whether changes made during the session should be saved to the profile. Recommended true."
}
},
"additionalProperties": false,
"description": "Options for using a persistent Hyperbrowser profile"
}
},
"additionalProperties": false,
"description": "Options for the browser session. Avoid setting these if not mentioned explicitly"
},
"numResults": {
"type": "integer",
"exclusiveMinimum": 0,
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Number of search results to return"
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — |
hyperbrowser:///sessions/advanced-privacy-and-anti-detectionThis page discusses Hyperbrowser's advanced privacy features and anti-detection capabilities for web scraping and automation.
hyperbrowser:///reference/api-reference/agentsThe "Agents" page in Hyperbrowser documentation discusses automated entities for web scraping and task execution.
hyperbrowser:///guides/ai-function-callingThe page discusses AI function calling features within Hyperbrowser for enhanced web scraping and automation.
hyperbrowser:///reference/api-referenceAPI Reference for Hyperbrowser provides detailed information on using its web scraping and automation features.
hyperbrowser:///agents/browser-useThe page discusses using Hyperbrowser for web scraping and automation tasks via browser interactions.
hyperbrowser:///reference/api-reference/agents/browser-useThe page explains how to effectively utilize browser features in Hyperbrowser for web scraping and automation tasks.
hyperbrowser:///guides/captcha-solvingHyperbrowser provides tools and guidance for CAPTCHA solving in web scraping and automation processes.
hyperbrowser:///agents/claude-computer-useThe page provides guidelines on using Claude with Hyperbrowser for effective web scraping and automation.
hyperbrowser:///reference/api-reference/agents/claude-computer-useThe page discusses using Claude for web scraping and automation with Hyperbrowser tools.
hyperbrowser:///web-scraping/crawlThe page discusses how to utilize Hyperbrowser for effective web crawling.
hyperbrowser:///reference/sdks/node/crawlThe "Crawl" page of Hyperbrowser details how to use the tool for web scraping and automated data extraction.
hyperbrowser:///reference/sdks/python/crawlThe Crawl section of Hyperbrowser’s documentation explains web scraping techniques and automation processes.
hyperbrowser:///reference/api-reference/crawlThe "Crawl" section of Hyperbrowser documentation explains how to use the tool for web scraping and automation tasks.
hyperbrowser:///get-started/quickstart/crawlingThe "Crawling" page of Hyperbrowser covers the tool's web scraping capabilities and how to implement them.
hyperbrowser:///sessions/extensionsThe page discusses extensions for Hyperbrowser, enhancing its web scraping and automation capabilities.
hyperbrowser:///reference/sdks/node/extensionsThe Extensions page for Hyperbrowser details available extensions that enhance web scraping and automation functionalities.
hyperbrowser:///reference/sdks/python/extensionsExplore Hyperbrowser extensions for enhanced web scraping and automation capabilities in your projects.
hyperbrowser:///reference/api-reference/extensionsThe page discusses extensions for Hyperbrowser that enhance its web scraping and automation capabilities.
hyperbrowser:///guides/extract-information-with-an-llmLearn how to extract information using a Large Language Model with Hyperbrowser.
hyperbrowser:///web-scraping/extractThe Extract page of Hyperbrowser provides guidelines for web scraping and data extraction techniques using the tool.
hyperbrowser:///reference/api-reference/extractThe Extract page of Hyperbrowser provides guidelines on data extraction methods and tools for web scraping.
hyperbrowser:///~gitbook/pdfHyperbrowser is a web scraping and automation tool, offering extensive documentation for users.
hyperbrowser:///integrations/langchainLangChain integrates with Hyperbrowser for enhanced web scraping and automation capabilities.
hyperbrowser:///sessions/live-viewThe Live View feature in Hyperbrowser allows real-time monitoring and interaction with web scraping tasks.
hyperbrowser:///integrations/llamaindexLlamaIndex documentation for integrating with Hyperbrowser for web scraping and automation tasks.
hyperbrowser:///guides/model-context-protocolThe page covers the Model Context Protocol used in Hyperbrowser for web scraping and automation.
hyperbrowser:///reference/sdks/nodeOverview of the Node module in Hyperbrowser for web scraping and automation.
hyperbrowser:///agents/openai-cuaThe page discusses the integration of OpenAI's CUA with Hyperbrowser for enhanced web scraping and automation capabilities.
hyperbrowser:///reference/api-reference/agents/openai-cuaOpenAI CUA for Hyperbrowser details integration and automation features for effective web scraping.
hyperbrowser:///sessions/overviewOverview of Hyperbrowser, a tool for web scraping and automation, detailing its features and functionalities.
hyperbrowser:///get-started/quickstart/playwrightThe page discusses using Playwright with Hyperbrowser for web scraping and automation tasks.
hyperbrowser:///sessions/profilesThe "Profiles" page in Hyperbrowser outlines how to manage user profiles for data scraping and automation tasks.
hyperbrowser:///reference/sdks/node/profilesThe "Profiles" page of Hyperbrowser covers user profiles and their management within the tool.
hyperbrowser:///reference/sdks/python/profilesThe "Profiles" page in Hyperbrowser documentation explains how to manage and use user profiles for web scraping tasks.
hyperbrowser:///reference/api-reference/profilesThe "Profiles" page in Hyperbrowser documentation explains how to manage and configure user profiles for scraping tasks.
hyperbrowser:///get-started/quickstart/puppeteerPuppeteer integration with Hyperbrowser enables web scraping and automation through headless browser control.
hyperbrowser:///reference/sdks/pythonThe page provides documentation on using Hyperbrowser with Python for web scraping and automation tasks.
hyperbrowser:///get-started/quickstartQuickstart guide for Hyperbrowser provides initial setup and functionality instructions for effective web scraping and automation.
hyperbrowser:///sessions/recordingsThe page covers Hyperbrowser's recording feature for efficient web scraping and automation processes.
hyperbrowser:///web-scraping/scrape"Scrape" page in Hyperbrowser documentation focuses on scraping data from web pages using the tool's features.
hyperbrowser:///reference/sdks/node/scrapeThe "Scrape" page of Hyperbrowser outlines techniques and tools for web scraping and automation.
hyperbrowser:///reference/sdks/python/scrapeThe page explains how to use Hyperbrowser for web scraping tasks.
hyperbrowser:///reference/api-reference/scrapeThe "Scrape" section of Hyperbrowser documentation explains web scraping techniques and automation features of the tool.
hyperbrowser:///get-started/quickstart/scrapingThe "Scraping" page in Hyperbrowser details how to extract data from websites using the tool's functionalities.
hyperbrowser:///guides/scrapingThe page covers web scraping techniques and documentation for using Hyperbrowser effectively.
hyperbrowser:///reference/sdksThe page discusses Hyperbrowser SDKs for web scraping and automation, including features and usage details.
hyperbrowser:///get-started/quickstart/seleniumSelenium integration with Hyperbrowser allows for enhanced web scraping and automation capabilities.
hyperbrowser:///sessions/overview/session-parametersThis page details session parameters for configuring Hyperbrowser's web scraping and automation features.
hyperbrowser:///reference/sdks/node/sessionsThe page discusses sessions in Hyperbrowser, detailing how to manage and utilize them effectively for web scraping tasks.
hyperbrowser:///reference/sdks/python/sessionsThe page discusses managing sessions in Hyperbrowser for effective web scraping and automation tasks.
hyperbrowser:///reference/api-reference/sessionsThe "Sessions" page in Hyperbrowser covers managing and utilizing sessions for web scraping and automation tasks.
hyperbrowser:///guides/using-hyperbrowser-sessionThe page describes how to use sessions in Hyperbrowser for efficient web scraping and automation.
hyperbrowser:///Hyperbrowser documentation provides an introduction to web scraping and automation using the Hyperbrowser tool.
hyperbrowser:///what-are-headless-browsersThe page explains headless browsers and their role in Hyperbrowser for web scraping and automation tasks.
| Endpoint | Transport | Authentication | Health | Observed |
|---|---|---|---|---|
| No verified remote endpoint is linked. | ||||
Install the selected package version with: npm install --save-exact hyperbrowser-mcp@1.0.25
Hyperbrowser MCP Server exposed 10 tools during independent protocol observation, including browser_use_agent, claude_computer_use_agent, crawl_webpages, create_profile, delete_profile, extract_structured_data, list_profiles, openai_computer_use_agent, and others.
The selected current version does not yet have completed public verification. Unknown does not mean clean or vulnerable.
Curated product and capability guides containing this catalog record.