Ragalgo
@kokogo100
About Ragalgo
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).
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ragalgo": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {
"RAGALGO_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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.
Frequently asked questions
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.
Basic information
More Other MCP servers
EverArt
modelcontextprotocolModel Context Protocol Servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments