How does Lyro know when a browser task has finished?

By polling. Watch Browser Task reports status as started, finished, stopped or failed, along with the current goal, the current URL and a screenshot from each step, so a long-running task is checked repeatedly rather than awaited in a single call.

How long does a task's file download link stay valid?

Not long. Download Task File returns a presigned URL for a file listed in the task's outputFiles, and that URL is temporary, so fetch the file promptly instead of storing the link. Calling the action again is how you get a fresh one.

What stops a browser task from running away with your time?

Stop Browser Task kills the run and its session outright, which is what the polling is for. When Watch Browser Task shows the agent stuck, looping or heading in the wrong direction, the session is ended and a fresh task started rather than left burning minutes.

Does the browser agent handle logins and CAPTCHAs?

It is built to. Run Browser Task drives multi-step flows such as log in, navigate, then extract, and handles dynamic content and CAPTCHAs, which is what separates it from a plain HTTP fetch. Any credentials the flow needs travel with the task you send, so treat them like any other secret.

Browser tool MCP integration

Starts cloud browser tasks, polls their progress step by step, kills a stuck run and fetches the files a task produced.

Connect Browser tool See all integrations

5actions available

Three actions you can hand over today

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

Run browser task
Lyro executes AI-powered browser automation workflows on demand. Support teams automate repetitive data entry without scripting knowledge.
Watch browser task
Lyro monitors task progress and returns results when complete. Agents track automation status without polling external dashboards.
Download task file
Lyro provides a download link for files generated by completed tasks. Users retrieve automation output without manual file transfers.

See all 5 actions

How businesses use Browser tool + Lyro

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

Get an answer that only exists behind a web flow
Lyro starts a browser task that logs in, navigates and extracts what it needs, polls the run for status, current goal and step screenshots, and kills it outright when the agent starts looping instead of progressing.
Run Browser TaskWatch Browser TaskStop Browser Task
Show the session and collect what it produced
Lyro shares the live URL so a person can watch the browser work in real time, then hands over a download link for any PDF, image or spreadsheet the task generated along the way.
Get Session Live URLDownload Task File

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 Browser tool actions it has and picks the ones a request needs.

01
Connect Browser tool
Authorize the Browser tool 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.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Browser tool actions that close it and chains as many as the request needs.
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

Browser tool · Lyro

Everything else about Browser tool

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

By polling. Watch Browser Task reports status as started, finished, stopped or failed, along with the current goal, the current URL and a screenshot from each step, so a long-running task is checked repeatedly rather than awaited in a single call.