Scrapfly
for LuumenAI
Scrape pages, pull structured data, and run crawls from the terminal
Connect Scrapfly and Luumen can fetch pages, render JavaScript, and pull structured fields out of the HTML while you stay in the terminal. Useful for checking a vendor status page, capturing what a customer-facing page actually renders, or collecting reference data during an incident. Starting a crawl is a held step you approve first.
The Scrapfly toolbox
12 tools: 11 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCapture Website ScreenshotCapture a full-page or viewport screenshot of a website.
- ReadCapture Screenshot Metadata (HEAD)Capture screenshot metadata without downloading the image body.
- ReadExtract Structured DataExtract structured data from HTML or other content using AI models, LLM prompts, or custom templates.
- ReadGet Scrapfly Account InformationRetrieve Scrapfly account information.
- ReadGet Crawler ArtifactDownload crawler artifact files in WARC or HAR format.
- ReadGet Crawler ContentsRetrieve extracted content from crawled pages.
- ReadGet Crawler StatusGet the current status of a crawler including progress, pages crawled, and completion state.
- ReadGet Crawler URLsRetrieve the list of discovered and crawled URLs from a crawler.
- ReadScrapfly ScrapePerform a web scraping request.
- ReadScrapfly Scrape POSTScrape web pages using POST method to send data in the request body.
- ReadScrape With PUTScrape web pages using PUT method with body payload.
- WriteCreate Scrapfly CrawlerCreate a new web crawler to recursively crawl an entire website. Approval by default
One prompt, start to finish
What a governed Scrapfly run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create scrapfly crawler — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Scrapfly — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
PostgreSQLQuery PostgreSQL state safely; maintenance held for approval.
MySQLQuery MySQL state safely; maintenance held for approval.
Microsoft SQL ServerQuery Microsoft SQL Server state safely; maintenance held for approval.Oracle DatabaseQuery Oracle Database state safely; maintenance held for approval.Put Scrapfly to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.