Skip to main content
Glama
Richgo Finance MCP

Richgo Finance MCP

by reallygood83

Richgo Finance MCP

Model Context Protocol (MCP) server for public data exposed by finance.richgo.ai.

It lets MCP clients search Korean stocks, fetch Richgo stock detail data, and use Richgo's ranking, undervaluation, AI ranking, curation, refreshed market dashboard, and Korea export-data screens from an assistant.

This project only calls public Richgo Finance endpoints by default. It does not bypass authentication or scrape private account data.

Tools

  • richgo_search_stock: search by Korean stock name or ticker.

  • richgo_get_stock_detail: fetch public detail for a ticker.

  • richgo_analyze_stock: search/alias resolve, then fetch compact analysis.

  • richgo_get_scores: score ranking table.

  • richgo_get_undervalued: undervalued stock tabs.

  • richgo_get_ai_rankings: AI ranking tab.

  • richgo_get_curation: curated screener buckets.

  • richgo_get_breakout: breakout/special signal endpoint.

  • richgo_get_exports_overview: Korea export overview, monthly export/import/trade balance history, sector-stock mappings, and export/employment momentum.

  • richgo_get_exports_nations: country-level export/import series and trade balances.

  • richgo_get_exports_region_ranking: regional export rankings and change rates.

  • richgo_get_market_ticker: headline market ticker snapshot, with freshness metadata for Korean index dates.

  • richgo_get_market_score_history: market environment score history.

  • richgo_get_market_investor_trend: foreign/institution/pension/individual investor flow trends.

  • richgo_get_market_valuation_history: market PER/PBR valuation history.

  • richgo_get_market_seasonality: market seasonality distribution and trajectory.

  • richgo_get_market_global_compare: global market comparison trajectories.

  • richgo_get_market_dashboard: bundled refreshed start/market page data.

  • richgo_get_market_api: generic /api/market/... wrapper.

  • richgo_get_public_api: constrained generic /api/... wrapper.

  • richgo_get_consensus_picks: merge Richgo scores, undervaluation, gap, and AI rankings into one ranked candidate list.

  • richgo_build_portfolio: build an integer-share portfolio from Richgo consensus signals for a budget and risk profile.

  • richgo_save_obsidian_report: save a generated portfolio report to a user-provided Obsidian vault path.

  • richgo_guided_portfolio: beginner-friendly portfolio wizard that uses MCP form elicitation when the client supports it.

  • richgo_service_catalog: list exposed services.

Related MCP server: Korean Stock MCP

Install

Easiest: npx

After this package is published to npm, you can run it directly with npx. Add this to your MCP client config:

{
  "mcpServers": {
    "richgo-finance": {
      "command": "npx",
      "args": ["-y", "richgo-finance-mcp"]
    }
  }
}

Restart your MCP client, then ask naturally:

셀트리온 리치고 데이터로 분석해줘

Developer install

git clone https://github.com/reallygood83/rfmcp.git
cd rfmcp
npm install
npm run build

Run Locally

npm start

On the original author's Mac, Homebrew Node was broken, so this bundled Node path was used:

export PATH=/Users/moon/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH
npm run build
npm start

Codex or Claude MCP config for local clone

{
  "mcpServers": {
    "richgo-finance": {
      "command": "node",
      "args": ["/absolute/path/to/rfmcp/dist/index.js"]
    }
  }
}

Example Prompts

You do not need to know the MCP tool names. Ask naturally:

  • 아이티센글로벌 리치고 데이터로 분석해줘

  • /rf 셀트리온 분석해줘

  • 삼성전자와 SK하이닉스 리치고 상세 지표 비교해줘

  • 리치고 저평가 total 상위 10개 보여줘

  • AI 랭킹 상위 종목을 요약해줘

  • 리치고 시작페이지에 새로 생긴 시장 현황 데이터를 요약해줘

  • 한국 수출 데이터 기준으로 섹터와 관련 종목을 뽑아줘

  • 외국인과 기관 수급 흐름을 리치고 시장 데이터로 보여줘

  • 리치고 컨센서스 기준으로 오늘 투자 매력 높은 종목 10개 뽑아줘

  • 500만원 중립형 포트폴리오 만들어줘

  • 초보자용 리치고 포트폴리오 마법사 시작해줘

  • 나는 잘 모르니까 질문하면서 300만원 투자 전략 만들어줘

  • 오늘 리치고 기준으로 뭐가 제일 좋아?

  • 1000만원이면 몇 종목을 몇 주씩 사면 좋을까?

  • 이 결과를 내 Obsidian 볼트에 보고서로 저장해줘

Natural Language Routing

Most MCP clients choose tools from the descriptions below. These are the intended natural-language routes:

User says

Preferred tool

What happens

삼성전자 분석해줘, 005930 리치고로 봐줘

richgo_analyze_stock

Resolves the stock and returns compact Richgo detail.

저평가 상위 10개, AI 랭킹 보여줘

richgo_get_undervalued / richgo_get_ai_rankings

Returns the requested screen.

수출 데이터로 투자 전략, 한국 수출 데이터 보여줘

richgo_get_exports_overview / richgo_get_exports_nations

Returns export/import/trade-balance history and sector-stock export mappings.

시장 현황, 시장 위험도, 계절성, 수급 흐름

richgo_get_market_dashboard / market-specific tools

Returns the refreshed Richgo start/market page data bundle or focused market series.

오늘 투자 매력 높은 종목, 뭐가 좋아?, 컨센서스 픽

richgo_get_consensus_picks

Combines scores, undervaluation, gap, and AI ranking into one candidate list.

500만원 포트폴리오, 몇 주씩 살까?, 예산으로 전략 짜줘

richgo_build_portfolio

Builds an integer-share portfolio with cash balance and risks.

초보자용, 질문하면서 도와줘, 마법사 시작

richgo_guided_portfolio

Uses form elicitation when supported, then builds the portfolio.

Obsidian에 저장, 볼트에 보고서로 저장

richgo_save_obsidian_report

Saves only when a vault path is provided or configured privately.

Market ticker freshness

richgo_get_market_ticker and the ticker section inside richgo_get_market_dashboard add a freshness object. Check it before writing KOSPI/KOSDAQ values as "current" market levels.

  • status: "verify_before_current_use" means the Korean index ticker date is older than the estimated latest Korea regular-session close.

  • expectedLatestKoreaCloseDate is estimated in Asia/Seoul time: after 16:00 KST on weekdays it expects today's close; before then it expects the previous weekday; weekends roll back to Friday.

  • Korean public holidays are not modeled, so treat the warning as a guardrail, not as an exchange-calendar substitute.

Optional Slash Command

This repo includes a Claude-style slash command template at commands/rf.md. Install it as /rf with:

mkdir -p ~/.claude/commands
cp commands/rf.md ~/.claude/commands/rf.md

After that, use prompts like:

/rf 셀트리온 분석해줘

The /rf command is tuned to produce data-backed Korean reports, not just a metric dump. It should connect revenue, profitability, cash flow, financial safety, valuation, and Richgo percentile signals into a concrete story that is easy to understand.

Portfolio and Obsidian reports

The portfolio tools intentionally do not hardcode a personal vault path. This keeps the published MCP reusable for other users.

Recommended natural-language flow:

초보자용 리치고 포트폴리오 마법사 시작해줘

If your MCP client supports form elicitation, the server asks for budget, risk profile, number of stocks, and whether to save to Obsidian. If the client does not support elicitation, call:

500만원 중립형 포트폴리오 만들어줘

To save Obsidian reports, either pass vaultPath in the tool call:

{
  "budget": 5000000,
  "riskProfile": "balanced",
  "vaultPath": "/absolute/path/to/your/vault",
  "noteDir": "Richgo"
}

Or keep the path in your private shell/MCP environment:

export RICHGO_OBSIDIAN_VAULT_PATH='/absolute/path/to/your/vault'

Do not commit personal vault paths to this repository.

Optional auth

Public endpoints work without auth. If you legitimately need login-only Richgo features, set your own cookie:

export RICHGO_COOKIE='...'

This server does not bypass authentication.

Disclaimer

Richgo Finance data is informational only and is not investment advice. Final investment decisions and responsibility belong to the user.

Available Tools

11 tools
richgo_analyze_stockResolve and analyze stockB

Resolve a user stock query through Richgo search/local aliases, fetch detail, and return a compact analysis payload.

Inputs: query (required), includeRaw.

richgo_get_ai_rankingsGet Richgo AI rankingsA

Fetch Richgo AI ranking tab with country, market, sort, top, and tier filters.

Inputs: country, market, sort, top, +1 more.

richgo_get_breakoutGet Richgo breakout/special signalsB

Fetch Richgo breakout/special-signal results. The site may return empty arrays for some signal types.

Inputs: type, limit.

richgo_get_curationGet Richgo curationC

Fetch a Richgo curated screener bucket such as compound_quality, income_safe, chart_breakout, health_quality, industrial_growth, it_stability, or consumer_margin.

Inputs: key.

richgo_get_market_apiGet Richgo market API pathA

Generic wrapper for public /api/market/{path} endpoints discovered in the app bundle. Use for market status endpoints not yet promoted to a first-class tool.

Inputs: path (required), params.

richgo_get_public_apiGet constrained Richgo public APIC

Constrained GET wrapper for public /api/... Richgo endpoints. This is useful while mapping newly discovered site services.

Inputs: path (required), params.

richgo_get_scoresGet Richgo score rankingB

Fetch the Richgo score/screener table with optional market, sort, tier, period, and limit filters.

Inputs: market, sort, tier, period, +1 more.

richgo_get_stock_detailGet Richgo stock detailA

Fetch public Richgo Finance detail for a stock ticker, including valuation, cash flow, safety, percentiles, and reports when available.

Inputs: ticker (required), compact.

richgo_get_undervaluedGet Richgo undervalued stocksB

Fetch Richgo undervalued-stock service. Modes mirror the site tabs: total, ttm, gap, composite, analyst, risky.

Inputs: mode, limit.

richgo_search_stockSearch Richgo stocksB

Search Richgo Finance for a stock by Korean name, partial name, or code. Returns matching stock candidates.

Inputs: query (required), limit.

richgo_service_catalogList Richgo MCP servicesA

Show all Richgo Finance services currently exposed by this MCP server.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools have distinct purposes (search vs. analysis vs. various screeners), but the generic wrappers (richgo_get_market_api, richgo_get_public_api) and overlap between richgo_analyze_stock and richgo_get_stock_detail (both fetch detail) could cause confusion for an agent.

    Naming Consistency5/5

    All tools follow a consistent 'richgo_verb_noun' pattern in snake_case, making it easy to predict the action and resource for each tool.

    Tool Count5/5

    With 11 tools covering search, analysis, multiple screeners, and generic wrappers, the count is well-scoped for a financial data server—neither too few nor too many.

    Completeness4/5

    The server covers essential stock research operations (search, detail, analysis, screeners) and includes generic wrappers for future endpoints. Minor gaps like historical data or news are not explicitly present, but the wrappers mitigate this.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Provides access to Korean financial news and market data (stocks and crypto) with AI-ready mathematical scoring to prevent hallucinations. Includes tools for news retrieval, chart analysis, financial statements, tag matching, and trend analysis.
      67 npm
      5
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides access to Korean stock market data, including stock listings, daily historical records, and 10-minute intraday candles via FinanceDataReader and Naver APIs. It enables users to search for stocks, retrieve detailed profiles, and calculate technical indicators locally.
      -
    • F
      license
      A
      quality
      D
      maintenance
      Provides technical analysis for Korean and US stocks through natural language queries. Enables users to analyze stock charts, search for tickers, and access technical indicators like RSI and MACD within Claude Desktop and other MCP clients.
      8
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time Korean stock market data, including stock prices, rankings, investor trends, and derivatives, via the Korea Investment & Securities OpenAPI. Enables AI models to query and analyze Korean financial data through natural language.
      -