Why does Lyro check status before returning crawl data?

Trigger Site Crawl returns a snapshot_id, not the data. Download Scraped Data called before the job finishes yields empty or partial results, so Lyro polls Check Crawl Status first and downloads only once the snapshot is complete. Large crawls are fetched incrementally because the payloads can be very large.

Does Web Unlocker always come back with usable HTML?

No. Some responses still contain a CAPTCHA challenge page or incomplete HTML even after the unlock attempt. Lyro inspects what came back rather than treating a 200 as success, and does not fall into an aggressive retry loop against the same URL.

Can Lyro narrow an existing dataset rather than crawling from scratch?

Yes. Browse Available Scrapers lists the pre-made datasets in Bright Data's marketplace and Filter Dataset applies custom criteria to one to generate a filtered snapshot. Bright Data marks that filtering action as BETA, so treat it as less settled than a straight crawl.

How does Lyro know which proxy location to request?

Get Available Countries returns the supported ISO 3166-1 alpha-2 codes and Get Available Cities returns the static network cities inside one of them, so a zone is configured against a location Bright Data actually serves. List Unlocker Zones shows which Web Unlocker zones are already provisioned on your account.

Brightdata MCP integration

Triggers crawls and downloads snapshots, runs SERP queries, retrieves pages behind bot protection, and checks which proxy locations exist.

Connect Brightdata See all integrations

10actions available

Three actions you can hand over today

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

Trigger site crawl
Lyro launches an asynchronous crawl of a website to extract content across all pages. Your team collects competitive intelligence or customer website data without browser automation.
Download scraped data
Lyro retrieves the completed crawl results from a finished job. Your team gets structured, cleaned data ready for analysis.
Serp search
Lyro scrapes search engine results for any query across multiple search engines. Your team monitors ranking, discovers competitors, and tracks keyword positions.

See all 10 actions

How businesses use Brightdata + Lyro

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

Run a crawl from trigger to downloaded data
Lyro starts an asynchronous crawl across a list of URLs or a whole domain, polls the snapshot until the job reports complete, then fetches the collected data incrementally rather than in one payload.
Trigger Site CrawlCheck Crawl StatusDownload Scraped Data
Pull search results and pages that block bots
Lyro runs a SERP query for rankings, trending topics or competitive research, and retrieves pages that need JavaScript rendering or defeat automated access through a configured Web Unlocker zone.
SERP SearchWeb UnlockerList Unlocker Zones
Start from a marketplace dataset instead of a crawl
Lyro lists the pre-made scrapers Bright Data publishes and applies custom filter criteria to one, generating a narrower snapshot without standing up a crawl for a source that already exists.
Browse Available ScrapersFilter Dataset
Configure a zone against a real location
Lyro lists the ISO 3166-1 alpha-2 country codes Bright Data supports and the static network cities inside the country you pick, so a proxy zone is provisioned against a location that exists.
Get Available CountriesGet Available Cities

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 Brightdata actions it has and picks the ones a request needs.

01
Connect Brightdata
Authorize the Brightdata 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 Brightdata 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

Brightdata · Lyro

Everything else about Brightdata

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

Trigger Site Crawl returns a snapshot_id, not the data. Download Scraped Data called before the job finishes yields empty or partial results, so Lyro polls Check Crawl Status first and downloads only once the snapshot is complete. Large crawls are fetched incrementally because the payloads can be very large.

Every action available in Brightdata

All 10 actions your agent can call on Brightdata, straight from the live MCP connection.

Trigger site crawl
Trigger an asynchronous site crawl job to extract content across multiple pages or entire domains.
Browse available scrapers
List all available pre-made scrapers (datasets) from Bright Data's marketplace.
Filter dataset
Apply custom filter criteria to a marketplace dataset (BETA).
Get available cities
Get available static network cities for a given country.
Get available countries
List available countries and their ISO 3166-1 alpha-2 codes.
Download scraped data
Retrieve the scraped data from a completed crawl job by snapshot ID.
Check crawl status
Check the processing status of a crawl job using snapshot ID.
List unlocker zones
List your configured Web Unlocker zones and proxy endpoints.
Serp search
Perform SERP (Search Engine Results Page) searches across different search engines using Bright Data's SERP Scrape API.
Web unlocker
Bypass bot detection, captcha, and other anti-scraping measures to extract content from websites.