jevcrawl vs Scrapfly

jevcrawl

Three compact, typed MCP tools return verbatim passages with source URLs, cost and stop reasons, and errors arrive as codes with instructions. The project is three days old and alpha, it depends on TypeSafe's paid Jev API, which is in early access with no free tier found, and it does not block crawls of private or local addresses.

Scrapfly

The error catalogue documents HTTP status, retry behaviour and billing for over 100 codes. The MCP server loads 61 tools at once.

jevcrawl

1. Phrase goal as one specific question and start with max_pages between 10 and 30
2. Check stats.stopped_because and stats.degraded, and read uncertain before reporting that something is missing
3. Use scrape without a goal when you need a whole page, since it makes no paid Jev call and needs no key
4. Handle {"error": code, "message": ...} results, for example auth_error means TYPESAFE_API_KEY is missing or rejected
5. Pages in stats.needs_js_urls were not read. Tell the user rather than guessing their content

Scrapfly

1. Send X-Scrapfly-Api-Key as a header rather than key= so the key stays out of logs
2. Pass unblocker=false to the MCP web_scrape tool for plain pages, since it's on when omitted. asp is the deprecated alias
3. Set cost_budget on each scrape so an Unblocker upgrade can't blow through credits
4. Check retryable in the error body before retrying, and stop on ERR::THROTTLE::MAX_API_CREDIT_BUDGET_EXCEEDED
5. Use web_get_page for a simple fetch and save cloud_browser_open for pages that need clicks