{
  "markdown": "# RagAlgo: Dynamic RAG Engine for AI Reliability\n\n[![npm version](https://img.shields.io/npm/v/ragalgo-mcp-server.svg)](https://www.npmjs.com/package/ragalgo-mcp-server)\n[![npm downloads](https://img.shields.io/npm/dm/ragalgo-mcp-server.svg)](https://www.npmjs.com/package/ragalgo-mcp-server)\n[![GitHub stars](https://img.shields.io/github/stars/kokogo100/ragalgo-mcp-server?style=social)](https://github.com/kokogo100/ragalgo-mcp-server)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-blue)](https://modelcontextprotocol.io)\n\n> **\"Your AI is an Analyst, NOT a Day Trader.\"**\n\n\nRagAlgo is an **MCP Server** that provides **mathematically scored financial context** (Korean Stocks/Crypto) to AI agents.\nWe focus on **\"State-of-Truth\"** (Daily Closed Data) to prevent AI hallucinations caused by real-time market noise.\n\n- **Analyst, Not Broker:** We provide \"Daily Analysis Reports\" (Post-Market), not real-time tick data.\n- **Scored Context:** Instead of raw prices, we give you \"Scores\" (0~100) and \"Zones\" (Forest vs Tree).\n- **Global Market Specialist:** Optimized for US, UK, JP, KR, and Crypto.\n\n👉 **[Official Website (ragalgo.com)](https://www.ragalgo.com)**\n\n---\n\n## 📖 Architecture & Whitepaper\n\nDiscover why RagAlgo is the **\"Hippocampus\"** for Agentic AI, not just another RAG.\n\n### 🏗️ Data Pipeline Architecture\n\nOur production system on Railway processes global financial data 24/7:\n\n```\n┌─────────────────────────────────────────────────────────────────────────────┐\n│                        RagAlgo Data Pipeline (Railway)                      │\n├─────────────────────────────────────────────────────────────────────────────┤\n│                                                                             │\n│  📥 COLLECT              🔍 FILTER              🏷️ TAG           📊 SCORE  │\n│  ─────────────          ──────────────         ─────────        ──────────  │\n│  • KR-News-Collector    • filter-worker-1      • tag-worker     • Gemini-1  │\n│  • US-News-Collector    • filter-worker-2      • Meta-Hierarchy • Gemini-2  │\n│  • UK-News-Collector    • filter-worker-3      •   Worker       • ...       │\n│  • JP-News-Collector    • ibkr_filter_worker3  │                • Gemini-7  │\n│  • research-collector   │                      │                │           │\n│                         │                      │                │           │\n│  ════════════════════════════════════════════════════════════════════════  │\n│                                    ↓                                        │\n│                      📦 SNAPSHOT (Daily 18:00 KST)                          │\n│                      ──────────────────────────────                         │\n│                      • KR-Snapshot  • US-Snapshot                           │\n│                      • UK-Snapshot  • JP-Snapshot                           │\n│                      • CRY-Snapshot • Unified-Snapshot                      │\n│                                    ↓                                        │\n│                          🚀 SERVE (MCP Server)                              │\n│                          ─────────────────────                              │\n│                          • RagAlgo-Service (SSE/stdio)                      │\n│                          • ragalgo-relay-server (WebSocket)                 │\n│                                                                             │\n└─────────────────────────────────────────────────────────────────────────────┘\n```\n\n![RagAlgo Architecture](./architecture.png)\n\n*   **[Vision Whitepaper (The Hook)](./docs/RagAlgo_Report_EN.md)**\n    *   **Concept**: Why RagAlgo is a \"Semantic Digital Twin\" (SDT) using the Hippocampus analogy.\n    *   **Value**: Explains the \"Self-Growing Taxonomy\" and \"Data Flywheel\" effect.\n*   **[Technical Report (The Proof)](./docs/CKN_Architecture_EN.md)**\n    *   **Deep Dive**: Detailed anatomy of the Contextual Knowledge Network (CKN).\n    *   **2025 Trend**: How RagAlgo serves as the memory layer for **Agentic AI** (e.g., PepsiCo/Salesforce Agentforce).\n\n---\n\n## 💡 Why \"Daily Close\"?\n\nUsers often ask: *\"Why isn't the chart data real-time?\"*\n\n**Because AI performs better with clarity.**\nReal-time tick data is full of noise and volatility. If you feed an LLM raw live prices, it often hallucinates patterns that don't exist.\n\nRagAlgo acts like a **Professional Technical Analyst** who works after the market closes:\n1.  **Wait for the dust to settle** (Market Close).\n2.  **Analyze the day's battle** (Daily Candle & Aux Indicators).\n3.  **Deliver a \"Confirmed Strategy\"** to your AI.\n\nUse RagAlgo to build **\"Investment Advisors\"**, not \"High-Frequency Trading Bots\".\n\n---\n\n## 🚀 Quick Start\n\n### Claude Desktop Configuration\n\nAdd this to your config file:\n- **Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n- **Mac:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n\n#### ☁️ Cloud Mode (Recommended - No installation required)\n```json\n{\n  \"mcpServers\": {\n    \"ragalgo\": {\n      \"url\": \"https://ragalgo-service-production.up.railway.app/sse\",\n      \"env\": {\n        \"RAGALGO_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n#### 📦 Local Mode (Requires Node.js)\n```json\n{\n  \"mcpServers\": {\n    \"ragalgo\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"ragalgo-mcp-server\", \"--stdio\"],\n      \"env\": {\n        \"RAGALGO_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n> **Tip:** You can get a **Free 1,000 Call Key** instantly at [RagAlgo Dashboard](https://www.ragalgo.com/dashboard).\n\n---\n\n## 📚 Usage Examples (Cookbook)\n\nWe have a **dedicated repository** for practical examples to help you get started quickly.\nPlease visit the **[RagAlgo Examples Repository](https://github.com/kokogo100/ragalgo-examples)**.\n\n### What's Inside?\n- **8 Step-by-Step Recipes:** From basic data fetching to advanced AI agents.\n- **Skeleton Code + Prompts:** Copy-paste ready resources.\n- **Scenarios:**\n  - 🐣 **Basic:** Get stock scores in 5 minutes.\n  - 🧪 **Intermediate:** Verify technical signals with AI.\n  - 🚀 **Advanced:** Build an autonomous reasoning agent (Mock Trading Audit).\n  - ☕ **Morning Briefing:** Create a bot that emails you a daily market summary.\n\n> **\"Skeleton + Prompt\" Approach:** We provide the ingredients. You ask ChatGPT/Claude to cook!\n\n---\n\n## 🌍 Supported Markets & Roadmap\n\nRagAlgo is expanding its CKN coverage globally. Currently, **US, UK, Japan, Korea, and Crypto** markets are fully supported.\n\n| Market | Asset Class | Status |\n| :--- | :--- | :--- |\n| **🇰🇷 Korea** | KOSPI / KOSDAQ | **🟢 Live** (Real-time Sentiment & Charts) |\n| **🇺🇸 USA** | NYSE / NASDAQ | **🟢 Live** (Daily Scored Context) |\n| **🇯🇵 Japan** | Nikkei 225 | **🟢 Live** (Daily Scored Context) |\n| **🇬🇧 UK** | LSE | **🟢 Live** (Daily Scored Context) |\n| **🪙 Crypto** | Global (Upbit/Binance) | **🟢 Live** (Real-time Sentiment & Charts) |\n\n---\n\n## 🛠 Tools\n\n> **⚠️ CORE CONCEPT: Scored vs Raw**\n> - **`get_news_scored` (Default):** Returns only significant news (Scores ≠ 0). Best for AI decision making.\n> - **`get_news` (Raw):** Returns ALL news including noise. Use this ONLY if you need raw data feed.\n\n| Tool | Description |\n|------|-------------|\n| `get_news_scored` | **[RECOMMENDED]** News **WITH** AI Sentiment Scores (-10 ~ +10). Filters out noise. |\n| `get_news` | **[Advanced]** Raw News **WITHOUT** scores. Includes 0-score noise. Use only if you build your own scorer. |\n| `get_chart_stock` | **[Core]** Global Stock (US/UK/JP/KR) Technical Analysis (Daily Close). |\n| `get_chart_coin` | **[Core]** Global Crypto Technical Analysis (Daily Close). |\n| `get_snapshots` | **[Best]** Market Overview (News + Chart + Trend) in one call. |\n| `get_financials` | Corporate Financials (Quarterly/Yearly). |\n| `search_tags` | Convert names (e.g., \"Samsung\") to RagAlgo Tags. |\n\n---\n\n## 📡 Real-time WebSocket (Business Tier)\n\nFor users who *really* need live data (e.g., for monitoring dashboards), we offer a WebSocket stream.\n*Note: This is strictly for monitoring, not for LLM inference context.*\n\n- **Access:** Business Plan subscribers (Includes 30 connections).\n- **Address:** `wss://ragalgo-relay-server-1-production.up.railway.app`\n- **Guide:** See [Developer Docs](https://www.ragalgo.com/docs) for implementation details.\n\n---\n\n## 💬 Support\n\n- **Website:** [ragalgo.com](https://www.ragalgo.com)\n- **Email:** support@ragalgo.com\n",
  "bytes": 8507,
  "sha": "9b835c40777d479971206a3461552ea979c3662fe186e607298677b0fefb6248",
  "repo_slug": "kokogo100/ragalgo-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kokogo100_ragalgo_31ce6a15/readme"
}