Classify website changes
When MrScraper detects a change on a monitored page, have Pipeless Recommendations judge whether the change is significant before anyone is alerted.
See all MrScraper + Pipeless Recommendations integrations or talk to a human
Opens Claude with Knit filled in: click Continue. Claude web and desktop share one connector list. Or paste this link in Settings > Connectors > Add custom connector.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents claude
Run in your own terminal, then restart Claude Code. Adds the server, the Knit skill and a CLAUDE.md note.
Turn on developer mode, then create a connector named Knit with this link and No Auth.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents codex
Run in your own terminal (not through Codex), then start a new Codex session.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents antigravity
Run in your own terminal, then reload MCP servers (/mcp in the CLI, refresh in the IDE).
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents cursor
Run in your own terminal, restart Cursor, then paste the note it prints into User Rules.
Google for Startups AcceleratorHow Knit builds this workflow
The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.
MrScraper Explore MrScraper →
TriggersFires when a scrape, crawl or robot run finishes in MrScraper.
Fires when MrScraper returns a new batch of extracted data.
Fires when MrScraper detects a change on a monitored page.
Extracts the content of a web page with MrScraper.
Starts a crawl of a whole site in MrScraper.
Runs a saved scraper, task or robot in MrScraper.
Pipeless Recommendations Explore Pipeless Recommendations →
TriggersFires when Pipeless Recommendations returns a completion, prediction or other result.
Fires when a request to Pipeless Recommendations errors or times out.
Fires when a fine-tuning job in Pipeless Recommendations finishes.
Sends a prompt to Pipeless Recommendations and returns the model's response.
Sends text, an image or other data to Pipeless Recommendations and returns the model's output.
Uses Pipeless Recommendations to classify or extract structured data from text or images.
More MrScraper + Pipeless Recommendations workflows
See all MrScraper + Pipeless Recommendations integrations → · Browse the full workflow library →
Enterprise-grade security
Common questions
Can Knit build “Classify website changes” between MrScraper and Pipeless Recommendations?
Yes — describe it in the box above and Knit's Integrations Agent researches MrScraper and Pipeless Recommendations's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.
How long does it take to build?
Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.
Why send scraped pages to an AI model?
Scraped HTML and text are noisy. Passing each MrScraper result to Pipeless Recommendations lets you pull out prices, names or key points in a consistent shape instead of cleaning the data by hand.
Can the model decide which pages to scrape next?
Yes. You can have Pipeless Recommendations produce a list of URLs or search terms, then run a scrape in MrScraper for each one.