惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Vercel News
Vercel News
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
雷峰网
雷峰网
有赞技术团队
有赞技术团队
罗磊的独立博客
博客园 - 叶小钗
Jina AI
Jina AI
博客园 - 司徒正美
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
T
Tailwind CSS Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
阮一峰的网络日志
阮一峰的网络日志
Microsoft Security Blog
Microsoft Security Blog
大猫的无限游戏
大猫的无限游戏
量子位
MyScale Blog
MyScale Blog
V
Visual Studio Blog
博客园 - 聂微东
The Cloudflare Blog
Engineering at Meta
Engineering at Meta
小众软件
小众软件
宝玉的分享
宝玉的分享

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - calypso-so/soccer-rag-mcp-server
ag_21 · 2026-06-12 · via Hacker News: Show HN

World Cup Soccer RAG MCP

Ask an AI agent grounded questions about international soccer results, no setup ceremony required. This MCP server boots straight into a Calypso-powered World Cup demo corpus: 150 years of match history, ready for source-backed answers.

Built with Calypso. Learn more in the Calypso docs.

Kickoff

npx -y @calypsohq/soccer-rag-mcp-server

That is it. No API key, no dashboard setup, no copy-pasting secrets. The server connects to the same World Cup RAG corpus as the RAG landing demo.

Inside The Corpus

This is the source-grounded research surface behind the World Cup Results Demo:

  • 4 indexed CSV sources
  • 49,393 match results from 1872 to 2026
  • Results, tournaments, venues, shootouts, goalscorers, and historical team names
  • Fast grounded answers by default, with citations from the soccer results corpus
  • Read-only demo mode powered by calypso-rag-agent:worldcup

Source trail:

  • results.csv: match results and venues, 49,393 rows
  • shootouts.csv: shootout winners and first shooters
  • goalscorers.csv: scorers, penalties, and own goals
  • former_names.csv: historical team-name changes for 36 teams

Try Asking

  • Who are the best men's national soccer teams of all time? Rank them using the results corpus and cite your evidence.
  • Which national teams dominated each era of international soccer from 1872 to 2026?
  • Compare Brazil and Germany across World Cup eras using match results from the corpus.
  • How strong is home advantage in international soccer, and has it changed over time?
  • Does hosting a major tournament improve a country's performance? Use the corpus to show why or why not.
  • What patterns stand out in international penalty shootouts? Use shootouts.csv and cite examples.

What You Get

  • Grounded answers from calypso-rag-agent:worldcup
  • Citation-rich responses through the Calypso Responses API
  • Handy resources like soccer://corpus-info and soccer://starter-prompts
  • A clean ask-world-cup-soccer MCP tool for match-history questions
  • A read-only demo surface, so agents can explore safely

Claude Desktop Setup

Add this to your Claude Desktop MCP config:

{
  "mcpServers": {
    "world-cup-soccer": {
      "command": "npx",
      "args": ["-y", "@calypsohq/soccer-rag-mcp-server"]
    }
  }
}

Restart Claude Desktop, then ask Claude to use world-cup-soccer for grounded soccer questions. The primary tool is ask-world-cup-soccer.

Bring Your Own Key

Want to use your own Calypso project with upload and bucket tools enabled?

CALYPSO_API_KEY=sk-... npx -y @calypsohq/soccer-rag-mcp-server

BYOK mode switches from the public World Cup demo into your own Calypso knowledge workspace.

For Claude Desktop BYOK mode, add an env block:

{
  "mcpServers": {
    "world-cup-soccer": {
      "command": "npx",
      "args": ["-y", "@calypsohq/soccer-rag-mcp-server"],
      "env": {
        "CALYPSO_API_KEY": "sk-..."
      }
    }
  }
}

Development

npm install
npm test
npm run smoke:stdio