{
  "markdown": "# readhn\n\n<!-- mcp-name: io.github.xodn348/readhn -->\n\n[![PyPI](https://badge.fury.io/py/readhn.svg)](https://pypi.org/project/readhn/)\n[![Tests](https://img.shields.io/badge/tests-199%20passed-brightgreen)](https://github.com/xodn348/readhn)\n[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)](https://github.com/xodn348/readhn)\n[![MCP](https://img.shields.io/badge/MCP-Registry-blue)](https://registry.modelcontextprotocol.io/v0.1/servers?search=readhn)\n\nAI-native HackerNews MCP Server. Find HN content that matters with explainable quality signals.\n\n## What It Does\n\n**Discover** — Filter stories by keywords, scores, time. Get ranked results with quality signals.\n\n**Trust** — Find domain experts. See who's talking and why they matter. EigenTrust propagation from seed experts.\n\n**Understand** — Every result explains WHY. 5 signals: practitioner depth (30%), thread depth (20%), expert involvement (20%), velocity (15%), references (15%).\n\n## Quick Start\n\n```bash\n# Install\npip install readhn\n\n# Auto-configure supported AI agents\nreadhn setup\n```\n\n`readhn setup` detects Claude Code, Codex, Cursor, Claude Desktop, Cline, Windsurf, and OpenCode config paths and adds the `readhn` MCP server.\n\nUseful setup flags:\n\n```bash\nreadhn setup --list              # Show detected agents\nreadhn setup --dry-run           # Preview config changes only\nreadhn setup --agents \"Cursor\"  # Configure only specific agents\n```\n\nAfter setup, your AI agent auto-discovers readhn and uses it when you ask HN questions.\n\n### Usage\n\nAsk your AI agent:\n- \"Show me top HN stories about Rust this week\"\n- \"Find experts who write about databases on HN\"\n- \"What did practitioners say about Kubernetes networking?\"\n\nThe agent calls readhn tools, gets results with quality signals, and explains why each result matters.\n\n### Configuration (Optional)\n\n```bash\nexport HN_KEYWORDS=\"ai,llm,rust,distributed-systems,databases\"  # Default filter keywords\nexport HN_MIN_SCORE=\"50\"                                         # Minimum story score\nexport HN_EXPERTS=\"tptacek,simonw,antirez,ept,jepsen\"           # Seed experts for trust\nexport HN_TIME_HOURS=\"24\"                                        # Time window\n```\n\n## How It Works\n\nWhen you ask HN questions, your AI agent uses these tools:\n\n- `discover_stories()` — Top stories filtered by keywords/score/time, ranked by quality signals\n- `search()` — Algolia search with explainable ranking\n- `find_experts()` — Find domain experts using EigenTrust on comment graph\n- `expert_brief()` — User profile + activity + trust score\n- `story_brief()` — Story + top comments + signals in one call\n- `thread_analysis()` — Full comment tree with quality signals per comment\n\nEvery response includes signals breakdown: why each result was chosen.\n\n## License\n\nMIT\n",
  "bytes": 2797,
  "sha": "16d3c9bd9c8493ad34412a87a7d83cab1aff352caea1f94a4f9701448ea6e2e9",
  "repo_slug": "xodn348/hnmcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_xodn348_readhn_2b52a1c1/readme"
}