Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-10 · high
Maintainers call it likely the last release before version 0.5, pairing it with 0.4.12's self-tuning crawl rate.
Why now: Scrapling shipped 0.4.13 on August 9, covered here in the August 10 briefing, with maintainers flagging it as the last release before v0.5.
Scrapling released version 0.4.13 on August 9 with XMLFeedSpider and companion classes that iterate feed entries directly, per the project's GitHub release notes. For anyone scraping feeds for an agent to read, that's one less spider to write by hand.
The release also reworks Scrapling's MCP server. Maintainers flagged 0.4.13 as likely the last release before version 0.5, per the GitHub changelog. That's a checkpoint to test before the interface changes again.
The update follows 0.4.12, which added AutoThrottle so a spider adjusts its own crawl rate. Before that, a developer had to hand-set a fixed download_delay and guess right. Pair the two and a scraper finds feed entries on its own, then slows down automatically when a site pushes back, no tuning required.
The feed spiders are convenience. The MCP rework is the bigger signal, a bet that Scrapling's next users are agents calling tools directly, not developers writing scrapy-style scripts. If v0.5 keeps expanding the MCP server rather than adding more spider types, that bet is paying off.
Each link below shares sources, entities, or timing with this story.
D4Vinci/Scrapling is a Python scraping framework whose standout feature is adaptive element tracking. It fingerprints elements by tag, text, attributes, and sibling/parent relationships, so selectors keep working after a redesign. It bundles an MCP server that pre-extracts tar...
774x faster than BeautifulSoup+Lxml. Parser learns from website changes and auto-relocates elements. v0.4 adds MCP server integration, Cloudflare Turnstile bypass, concurrent spider with pause/resume, automatic proxy rotation. Drop-in MCP tool call for structured web scraping....
Scrapling learns element "signatures" and relocates them when a page's structure changes, avoiding brittle CSS/XPath, and ships an MCP server that extracts targeted content before handing it to the model (GitHub). It handles anti-bot challenges like Cloudflare Turnstile with b...
A breaking change, and an unusually security-conscious default for an MCP server. It also split tools into one-shot (fetch, bulk_fetch, stealthy_fetch) and session-based variants that retain cookies and fingerprints, and added a Response.markdown() that strips scripts, styles...
If you wrote an MCP server before July, it's on a protocol shape the maintainers have already removed. Not deprecated-with-a-migration-window. Removed from the spec. MCP lead maintainers David Soria Parra and Den Delimarsky published an updated roadmap on August 22, and the re...
First major enterprise observability platform to ship a production-grade MCP server. Feeds live logs, metrics, and traces directly into Claude Code, Cursor, Codex, GitHub Copilot, and VS Code. AI coding agents can now investigate production issues using real-time telemetry. MC...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.