xodn348 avatar

Readhn

xodn348/hnmcp

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.

tools
6
transport
STDIO
last updated
Mar 10, 2026

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

discover_storiesTop stories filtered by keywords/score/time, ranked by quality signals

Top stories filtered by keywords/score/time, ranked by quality signals

No parameter schema in public metadata yet.

searchAlgolia search with explainable ranking

Algolia search with explainable ranking

No parameter schema in public metadata yet.

find_expertsFind domain experts using EigenTrust on comment graph

Find domain experts using EigenTrust on comment graph

No parameter schema in public metadata yet.

expert_briefUser profile + activity + trust score

User profile + activity + trust score

No parameter schema in public metadata yet.

story_briefStory + top comments + signals in one call

Story + top comments + signals in one call

No parameter schema in public metadata yet.

thread_analysisFull comment tree with quality signals per comment

Full comment tree with quality signals per comment

No parameter schema in public metadata yet.

Sponsors

Readme

readhn

PyPI Tests Coverage MCP

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

View the full README on GitHub

Details

Repository
github.com/xodn348/hnmcp
Package
readhn
Transport
STDIO
Registry
MCP registry, active