MCP.so
ログイン

Ragalgo

@kokogo100

Ragalgo について

Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).

基本情報

カテゴリ

その他

ランタイム

node

トランスポート

stdio

公開者

kokogo100

投稿者

--_--+

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "ragalgo": {
      "command": "node",
      "args": [
        "dist/index.js"
      ],
      "env": {
        "RAGALGO_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Ragalgo?

Ragalgo is an MCP Server that provides mathematically scored financial context (Korean Stocks/Crypto) to AI agents, focusing on daily closed data to reduce AI hallucinations from real-time market noise. It delivers analysis reports instead of raw tick data, aimed at developers building reliable investment advisors.

How to use Ragalgo?

Configure it in Claude Desktop via Cloud (URL) or Local (npx) mode, setting the RAGALGO_API_KEY. A free 1,000-call key is available at the RagAlgo Dashboard. Start with the example repository for step-by-step recipes.

Key features of Ragalgo

  • Scored context (0–100) and Zones (Forest vs Tree)
  • Daily Close data for US, UK, JP, KR, and Crypto
  • Recommended scored news filtering (get_news_scored)
  • Core stock and crypto technical analysis charts
  • Unified market snapshots in one call
  • Corporate financials and search tags for assets

Use cases of Ragalgo

  • Build an AI “Investment Advisor” that uses post-market analysis
  • Create a daily morning briefing bot with market summary
  • Verify technical signals using AI-generated sentiment scores
  • Develop an autonomous reasoning agent for mock trading audits
  • Monitor global markets without real-time noise

FAQ from Ragalgo

Why does Ragalgo use daily close data instead of real-time?

Real-time tick data is noisy and can cause LLMs to hallucinate patterns. Daily close data provides a confirmed, cleaner state-of-truth for AI analysis.

What markets does Ragalgo support?

It fully supports Korea (KOSPI/KOSDAQ), USA (NYSE/NASDAQ), Japan (Nikkei 225), UK (LSE), and Global Crypto (Upbit/Binance).

Should I use get_news_scored or get_news?

Use get_news_scored for filtered, AI-scored news. Use get_news only if you need raw unfiltered data and plan to build your own scorer.

How can I get an API key?

Obtain a free 1,000-call key instantly from the RagAlgo Dashboard at ragalgo.com/dashboard.

Is there a real-time option available?

Yes, a WebSocket stream (wss://ragalgo-relay-server-1-production.up.railway.app) is available for Business Plan subscribers, intended for monitoring dashboards, not LLM inference.

コメント

「その他」の他のコンテンツ