Can Lyro write the extraction logic for a new Parsera scraper?

It can create the scraper and return the ID, but the code generation step sits behind a separate endpoint the toolkit does not expose. In practice Extract Data From Webpage is the more direct route - it takes a URL and field descriptions and needs no scraper object at all.

Can Lyro scrape a site that shows different content by country?

Yes. Run Scraper Template accepts a proxy country and optional cookies, and Get Proxy Countries returns the list Parsera supports, so Lyro can request the regional version of a page rather than whatever the default exit node happens to return.

What if the content is already in hand and does not need fetching?

Parse Content (Enhanced) takes raw HTML or text instead of a URL and supports pagination and different extraction modes, so Lyro can structure something a customer pasted into the chat without going back out to the site.

Which language model runs behind an extraction Lyro requests?

Get LLM Specifications returns standardised capabilities and pricing for the models Parsera supports across providers, so the economics are visible before a run. The extraction actions themselves expose no model-choice parameter, so Lyro reports those specifications rather than switching models mid-run.

Parsera MCP integration

Pulls named fields off a live URL, runs saved scrapers and agents through regional proxies, and clears out the ones no longer in use.

Connect Parsera See all integrations

13actions available

Three actions you can hand over today

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

List scrapers
Lyro shows all available scrapers and templates so you pick the right one for your data extraction task. This speeds up setup without building from scratch.
Extract data from webpage
Lyro pulls structured data from any webpage using AI-powered extraction to capture tables, lists, or specific fields. This retrieves data without writing scrapers.
Scrape with agent
Lyro runs a pre-built scraper on a URL to collect structured data automatically. This executes data extraction without manual copying.

See all 13 actions

How businesses use Parsera + Lyro

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

Pull named fields off a live page
Lyro sends the URL and a description of each field to Parsera and gets structured data back, so a question about what a page currently lists is answered without anyone writing a selector.
Extract Data From WebpageExtract MarkdownParse Content (Enhanced)
Run a saved scraper against a new address
When the shape of the page is already known, Lyro runs the existing template or agent on the URL in question and sets a proxy country where the site serves different content by region.
Run Scraper TemplateScrape With AgentGet Proxy Countries
Stand up a new scraper and confirm it can run
Lyro creates an empty scraper for the account, verifies the Parsera API is reachable, and reports the current model capabilities and pricing so the new source is set up against a model that fits.
Create ScraperHealth CheckGet LLM Specifications
Keep the scraper and agent list clean
Lyro lists what exists on the account, then deletes a scraper by its ID or removes an agent by name, so retired sources are not left sitting there being mistaken for current ones.
List ScrapersDelete ScraperRemove Agent

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

01
Connect Parsera
Authorize the Parsera 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 Parsera 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

Parsera · Lyro

Everything else about Parsera

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

It can create the scraper and return the ID, but the code generation step sits behind a separate endpoint the toolkit does not expose. In practice Extract Data From Webpage is the more direct route - it takes a URL and field descriptions and needs no scraper object at all.

Every action available in Parsera

All 13 actions your agent can call on Parsera, straight from the live MCP connection.

Create scraper
Create a new empty scraper for your account.
Delete scraper
Delete an existing scraper by its ID.
Extract data from webpage
Perform LLM-powered data extraction from a live webpage URL with specified attributes.
Extract markdown
Extract markdown content from a file or URL.
Get llm specifications
Retrieve standardized LLM capabilities and pricing specifications.
Get proxy countries
Retrieve the list of available proxy countries for web scraping requests.
Health check
Verify API availability and operational status.
List agents
Retrieve all available agents for the authenticated user.
List scrapers
List all templates and old scrapers for the authenticated user.
Parse content (enhanced)
Extract structured data from raw HTML or text content using AI with advanced options.
Remove agent
Delete an existing agent by name.
Run scraper template
Run a scraper template on a specified URL with optional proxy and cookies.
Scrape with agent
Run a previously generated scraper agent on a specific URL to extract structured data.