Parallel scraper and API skills

Site: parallel.ai

Parallel ships its own API and MCP server, and these skills sit alongside them: connecting an agent to Parallel's web search MCP, running a deep-research task through the CLI, and creating a web-change monitor in the app.

Working with Parallel

  • The MCP connection skill configures a real client, so the result is a working connection rather than a copied config block.
  • Monitor creation runs in the authenticated app, where monitor state is visible after the fact.

3 Parallel skills

Parallel scraping questions

Does Parallel have an API?
Yes — Parallel publishes both an API and an MCP server. These skills cover connecting to them and driving the app surfaces around them.
Is scraping Parallel legal?
Reading data that Parallel publishes publicly is generally treated as lawful in the US — hiQ v. LinkedIn found that scraping a public site does not by itself violate the Computer Fraud and Abuse Act. That is not the whole question: Parallel's terms of service, its robots.txt, the rate at which you request pages, and any personal or copyrighted data you collect all carry their own obligations, and the rules differ outside the US. These skills read public pages at human-scale rates and never bypass a login. Treat this as background, not legal advice.
What data can I extract from Parallel?
Monitor name, target URL and change criteria; deep-research task output; and the resolved MCP connection details.

Related hubs