I Built a Self-Hosted RSS Reader with AI Summarization, Translation, and an MCP Server

1. Miniflux

   1 104 9,558 9.7 Go

   Minimalist and opinionated feed reader

   

   Existing readers especially fail at the "full text in-app" requirement. Miniflux has a full-text fetch feature, but you have to opt in per feed. FreshRSS doesn't use Readability at all — it requires users to manually enter CSS selectors for each site. Both can do it with configuration, but neither does it by default. You end up clicking article titles and reading through cookie banners, ads, and paywalls.

2. Puter.js

   developer.puter.com featured

   Puter.js - The Backend for AI-Generated Apps. One-shot full-stack apps with your existing AI coding tool. Puter.js gives you Auth, Storage, DB, AI & more, with up to 90% fewer AI tokens than other backend platforms.

   

3. FreshRSS

   2 83 15,662 9.7 PHP

   A free, self-hostable news aggregator…

   

   Existing readers especially fail at the "full text in-app" requirement. Miniflux has a full-text fetch feature, but you have to opt in per feed. FreshRSS doesn't use Readability at all — it requires users to manually enter CSS selectors for each site. Both can do it with configuration, but neither does it by default. You end up clicking article titles and reading through cookie banners, ads, and paywalls.

4. oksskolten

   3 1 460 9.6 TypeScript

   🏔️ The AI-native RSS reader

   

5. servers

   4 460 89,291 9.4 TypeScript

   Model Context Protocol Servers

   

   Second, data consumption isn't limited to the app UI. Oksskolten has a built-in MCP (Model Context Protocol) server. The same 12 tools used by the in-app AI chat (search_articles, get_article, toggle_bookmark, etc.) are exposed externally via MCP. Claude Code, Claude Desktop, or any MCP client can access the article data.

6. readability

   5 60 11,384 4.8 JavaScript

   A standalone version of the readability lib

   

   Here's the pipeline: fetch the original article URL, extract content with Mozilla's Readability.js, remove noise with 600 custom patterns (ads, navigation, sidebars, trackers), convert to Markdown with Turndown, and store in SQLite.

7. to-markdown

   6 15 11,376 6.0 HTML

   🛏 An HTML to Markdown converter written in JavaScript

   

   Here's the pipeline: fetch the original article URL, extract content with Mozilla's Readability.js, remove noise with 600 custom patterns (ads, navigation, sidebars, trackers), convert to Markdown with Turndown, and store in SQLite.

8. piscina

   7 18 5,178 8.9 TypeScript

   A fast, efficient Node.js Worker Thread Pool implementation

   

   DOM parsing (jsdom + Readability + Turndown) is CPU-heavy, so it's offloaded to up to 2 Worker Threads via piscina, keeping the API event loop unblocked.

9. AppSignal

   www.appsignal.com featured

   Monitoring that respects your time & budget. APM, error tracking, and dashboards for modern web apps. Ten-minute setup, transparent flat pricing, and support from engineers who actually use the product.

   

10. defuddle

    8 5 8,706 9.7 TypeScript

    Get the main content of any page as Markdown.

    

    The noise-removal patterns were also informed by defuddle, an HTML sanitization library by Obsidian CEO Steph Ango, which has a comprehensive set of selector patterns for stripping ads and navigation elements.

11. FlareSolverr

    9 41 15,050 6.6 Python

    Proxy server to bypass Cloudflare protection

    

    For sites requiring JavaScript rendering, FlareSolverr (Headless Chrome) handles it.

Suggest a related project