Hyperbrowser

Hyperbrowser MCP integration

Fetches live pages as Markdown, JSON, or screenshots, runs crawl and extraction jobs to completion, and manages browser sessions and profiles.

Connect HyperbrowserSee all integrations

42actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

  • Fetch web page

    Lyro downloads a web page and returns its content in multiple formats. Your team extracts text, HTML, or screenshots from any URL without manual copying.

  • Start browser use task

    Lyro launches an asynchronous browser automation task. Your team automates repetitive web tasks and collects real-time data hands-free.

  • Stop browser use task

    Lyro halts a running browser automation task. Your team cancels runaway tasks and saves resources before they complete.

See all 42 actions

How businesses use Hyperbrowser + Lyro

Each card is one request a support team gets, and the Hyperbrowser actions Lyro runs to close it.

  • Pull a live page into the conversation

    Lyro searches the web for the right URL and fetches the page as HTML, Markdown, JSON, or a screenshot, so the answer reflects what the page says right now rather than what was indexed months ago.

    Search WebFetch Web PageCreate Scrape Job

  • Extract structured data from a set of pages

    Lyro starts an AI-powered extraction across one or more pages, polls the job until it reports complete, and returns the structured result rather than a raw page dump nobody can use.

    Start Extract JobGet Extract Job StatusGet Extract Job Result

  • Reuse a logged-in browser instead of starting cold

    Lyro creates a persistent profile that carries cookies and session state between runs, lists the profiles already on the account, and uploads the Chrome extension a particular task depends on.

    Create Hyperbrowser ProfileList ProfilesAdd Extension

  • Drive a browser task and review the run

    Lyro starts an asynchronous browser-use task from a plain instruction, retrieves the session recording afterwards so the run can be checked, and stops the session once the work is done.

    Start Browser Use TaskGet Session RecordingStop Session

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Hyperbrowser actions it has and picks the ones a request needs.

  1. 01

    Connect Hyperbrowser

    Authorize the Hyperbrowser account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.

  2. 02

    Tell your agent what you need

    Describe the job the way you would hand it to a teammate. Lyro maps it to the Hyperbrowser actions that close it and chains as many as the request needs.

  3. 03

    Watch it work

    The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.

    Get started free
Hyperbrowser · Lyro

Everything else about Hyperbrowser

Setup, permissions, and the limits of what Lyro can do inside Hyperbrowser.

  • Four. Start Browser Use Task, Start Claude Computer Use Task, Start CUA Task for OpenAI's Computer-Using Agent, and Start Gemini Computer Use Task each launch a different automation agent, and each has its own status, result, and stop action, so a long run can be polled or halted mid-flight.

Every action available in Hyperbrowser

All 42 actions your agent can call on Hyperbrowser, straight from the live MCP connection.

  • Add extension

    Add a new browser extension to Hyperbrowser for use in sessions.

  • Create hyperbrowser profile

    Creates a new persistent Hyperbrowser profile for storing browser state (cookies, sessions, etc.).

  • Create scrape job

    Initiate a new scrape job.

  • Create session

    Create a new browser session with custom stealth, proxy, and privacy settings.

  • Delete profile

    Delete a profile.

  • Fetch web page

    Fetch a web page and return content in various formats (HTML, Markdown, JSON, screenshot, etc.).

  • Get browser-use task status

    Retrieve the current status of a browser-use task.

  • Get claude computer use task result

    Retrieve the complete result and status of a Claude Computer Use task.

  • Get claude computer use task status

    Poll the execution status of a Claude Computer Use task.

  • Get crawl job status

    Retrieve the status and results of a specific crawl job.

  • Get crawl status

    Retrieve the current status of a specific crawl job.

  • Get cua task result

    Retrieve the status and results of a CUA (Claude User Agent) task.

  • Get cua task status

    Poll the execution status of a CUA task.

  • Get extract job result

    Fetch the status and results of a specific extract job.

  • Get extract job status

    Retrieve the status of an extract job.

  • Get gemini computer use task result

    Retrieve the current status and results of a Gemini Computer Use task.

  • Get hyperagent task result

    Retrieve the status and results of a HyperAgent task.

  • Get profile by ID

    Retrieves details of a specific Hyperbrowser profile by its UUID.

  • Get scrape job result

    Retrieves the status and results of a scrape job.

  • Get scrape job status

    Retrieve the current status of a specific scrape job.

  • Get session details

    Retrieve detailed information about a Hyperbrowser session by its ID.

  • Get session downloads URL

    Retrieve the downloads URL for a session.

  • Get session recording

    Retrieve the recording URL for a browser session.

  • Get session video recording URL

    Retrieve the video recording URL for a browser session.

  • Get web crawl result

    Retrieve the status and results of a web crawl job.

  • Get web crawl status

    Retrieve just the status of a web crawl job without the full results.

  • List extensions

    List all browser extensions.

  • List profiles

    List profiles.

  • List sessions

    List sessions with optional status filter.

  • Search web

    Perform a web search and retrieve results with titles, URLs, and descriptions.

The tools Hyperbrowser sits next to

Same connection, same setup. Pick the next one your team already uses.

Browse every integration

Ready to connect Hyperbrowser?

Authorize the account and your agent has all 42 actions from the first conversation.

Connect HyperbrowserTalk to sales
Support agent working at a laptop next to the Lyro mascot