Scrapfly MCP integration
Scrapes pages that block ordinary requests, crawls whole sites, captures screenshots, and returns extracted fields instead of raw HTML.
12actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Scrapfly scrape
Lyro scrapes webpages to extract product details, pricing, reviews, or content customers ask about. You get current information instantly to answer questions accurately.
Extract structured data
Lyro extracts structured data from websites using AI to identify prices, specs, and key information. Your team pulls organized data from unstructured pages for analysis.
Capture website screenshot
Lyro captures full-page screenshots of websites to document competitor pages or design changes. Your team tracks what competitors are doing without manual screenshots.
How businesses use Scrapfly + Lyro
Each card is one request a support team gets, and the Scrapfly actions Lyro runs to close it.
Fetch a page that blocks ordinary requests
Lyro scrapes the URL with JavaScript rendering and proxies configured, and switches to a POST or PUT request when the target expects a body rather than a plain fetch.
Scrapfly ScrapeScrapfly Scrape POSTScrape With PUTCrawl a whole site and collect what it finds
Lyro starts a recursive crawl, polls its progress and page count, and returns the crawled content as markdown, text, HTML, or JSON, or as a WARC or HAR archive.
Create Scrapfly CrawlerGet Crawler StatusGet Crawler ContentsGet Crawler ArtifactCapture how a page actually renders
Lyro takes a full-page or viewport screenshot with JavaScript rendered, or requests only the metadata when the image itself is fetched later in an async workflow.
Capture Website ScreenshotCapture Screenshot MetadataTurn a fetched page into structured fields
Lyro passes scraped HTML through an AI model, an LLM prompt, or a custom template, so a page comes back as the fields you asked for instead of markup someone still has to parse.
Extract Structured DataScrapfly ScrapeGet Crawler Contents
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 Scrapfly actions it has and picks the ones a request needs.
Connect Scrapfly
Authorize the Scrapfly 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.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Scrapfly actions that close it and chains as many as the request needs.
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
Scrapfly · Lyro
What can you do in Scrapfly without me setting anything up?
These, right away:
- Create scrapfly crawler
- Get scrapfly account information
- Capture website screenshot
Great, let's start with the first one.
FAQ
Everything else about Scrapfly
Setup, permissions, and the limits of what Lyro can do inside Scrapfly.
Some targets are API endpoints rather than pages and reject a plain fetch. Scrapfly Scrape covers the standard request, while Scrapfly Scrape POST and Scrape With PUT send a payload in the request body, so Lyro can reach endpoints that only answer to a specific method.
Every action available in Scrapfly
All 12 actions your agent can call on Scrapfly, straight from the live MCP connection.
Capture website screenshot
Capture a full-page or viewport screenshot of a website.
Capture screenshot metadata (head)
Capture screenshot metadata without downloading the image body.
Create scrapfly crawler
Create a new web crawler to recursively crawl an entire website.
Extract structured data
Extract structured data from HTML or other content using AI models, LLM prompts, or custom templates.
Get scrapfly account information
Retrieve Scrapfly account information.
Get crawler artifact
Download crawler artifact files in WARC or HAR format.
Get crawler contents
Retrieve extracted content from crawled pages.
Get crawler status
Get the current status of a crawler including progress, pages crawled, and completion state.
Get crawler urls
Retrieve the list of discovered and crawled URLs from a crawler.
Scrapfly scrape
Perform a web scraping request.
Scrapfly scrape post
Scrape web pages using POST method to send data in the request body.
Scrape with put
Scrape web pages using PUT method with body payload.
The tools Scrapfly sits next to
Same connection, same setup. Pick the next one your team already uses.
Brightdata
Triggers crawls and downloads snapshots, runs SERP queries, retrieves pages behind bot protection, and checks which proxy locations exist.
Exa
Answers a question with citations, extracts full page text, builds Websets of lookalike pages, and runs async research tasks that return reports.
Kibana
Checks Kibana and cluster health, finds the detection alerts that fired, builds dashboards and data views, and creates alerting rules and connectors.
Openperplex
Answer a question from live search results with citations, extract a linked page as text or markdown, and interrogate a document by URL.
Securitytrails
Pulls DNS, SSL, and infrastructure detail for a domain, queries the hosts and ips tables directly, and keeps ASI asset scope current.
Webscraping.ai
Answers questions about a live web page, extracts named fields as JSON, and pulls rendered HTML or specific elements by CSS selector.
Ready to connect Scrapfly?
Authorize the account and your agent has all 12 actions from the first conversation.