I built an hourly newspaper for e-ink (and turned the pipeline into an MCP server)
Description and use
An hourly automated news pipeline delivers 480x800 e‑ink pages, PDFs for reMarkable/Kindle, and an MCP API for agents.
Problem
Deliver timely, curated news to e‑ink readers and agents without manual editing.
Outcome
Hourly curated news delivered as e‑ink pages, PDFs, and an MCP API, with automated deduplication and ranking, achieving steady bot traffic and user adoption.
Workflow
- Collect 120 items from ~100 RSS feeds with feedparser
- Deduplicate by canonical URL and headline entity overlap
- Rank with Claude Haiku 4.5, fallback to rule‑based ranker
- Render 480x800 BMP, 800x480 panel, and PDF with Pillow
- Publish to S3 + CloudFront with change‑stamp manifest
Evidence
Every hour, a Lambda pulls about 120 items from ~100 RSS feeds, asks a small model to act as an editor, and typesets the result as a 480x800 one-bit page for the Xteink X4 e-ink reader
The same pipeline now produces a multi-page "Morning Paper" PDF for reMarkable and Kindle, a TRMNL plugin, and an MCP server that agents can call
- Record date: 2026-09-18T09:30:48.888Z