Summary
This server wraps HackerNews with quality scoring built in. It exposes six tools: discover_stories filters by keywords and time, search hits Algolia's API, find_experts runs EigenTrust on the comment graph to surface domain authorities, and story_brief pulls threads in one shot. Every result includes a breakdown of five ranking signals: practitioner depth, thread depth, expert involvement, velocity, and reference quality. You'd reach for this when you want HN content filtered by substance rather than just points, or when you need to find who actually knows what they're talking about in a thread. The setup command auto-configures Claude Desktop, Cursor, and other supported agents by detecting their config paths.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
readhn
AI-native HackerNews MCP Server. Find HN content that matters with explainable quality signals.
What It Does
Discover — Filter stories by keywords, scores, time. Get ranked results with quality signals.
Trust — Find domain experts. See who's talking and why they matter. EigenTrust propagation from seed experts.
Understand — Every result explains WHY. 5 signals: practitioner depth (30%), thread depth (20%), expert involvement (20%), velocity (15%), references (15%).
Quick Start
# Install
pip install readhn
# Auto-configure supported AI agents
readhn setup
readhn setup detects Claude Code, Codex, Cursor, Claude Desktop, Cline, Windsurf, and OpenCode config paths and adds the readhn MCP server.
Useful setup flags:
readhn setup --list # Show detected agents
readhn setup --dry-run # Preview config changes only
readhn setup --agents "Cursor" # Configure only specific agents
After setup, your AI agent auto-discovers readhn and uses it when you ask HN questions.
Usage
Ask your AI agent:
- "Show me top HN stories about Rust this week"
- "Find experts who write about databases on HN"
- "What did practitioners say about Kubernetes networking?"
The agent calls readhn tools, gets results with quality signals, and explains why each result matters.
Configuration (Optional)
export HN_KEYWORDS="ai,llm,rust,distributed-systems,databases" # Default filter keywords
export HN_MIN_SCORE="50" # Minimum story score
export HN_EXPERTS="tptacek,simonw,antirez,ept,jepsen" # Seed experts for trust
export HN_TIME_HOURS="24" # Time window
How It Works
When you ask HN questions, your AI agent uses these tools:
discover_stories()— Top stories filtered by keywords/score/time, ranked by quality signalssearch()— Algolia search with explainable rankingfind_experts()— Find domain experts using EigenTrust on comment graphexpert_brief()— User profile + activity + trust scorestory_brief()— Story + top comments + signals in one callthread_analysis()— Full comment tree with quality signals per comment
Every response includes signals breakdown: why each result was chosen.
License
MIT
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →