How do I use Stock MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Stock MCP Server analyze NVDA's RSI and MACD for the past month" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

Stock MCP Server

by Juuuuuuni

Overview Schema Source Related Servers Discussions Admin

Python

Remote

📈 Stock MCP Server

This is a Model Context Protocol (MCP) server that provides technical analysis and strategy-based screening for Korean and US stocks. You can perform chart analysis and stock screening using natural language in MCP-compatible clients such as Claude Desktop and Claude Code.

✨ Features

🇰🇷 Korean Stock Analysis — OHLCV + technical indicators for all KOSPI/KOSDAQ stocks based on pykrx
🇺🇸 US Stock Analysis — NYSE/NASDAQ stocks based on yfinance + market cap/PER/52-week high/low
🔍 Stock Search — Find stock codes by stock name (Korean stocks)
📊 10 Momentum Strategies + 7 Breakout Strategies — From Golden Cross to VCP
🎯 Two Screening Philosophies — 🐎 Catching the Running Horse vs 🌱 Finding the Horse About to Run
🔎 Multi-stage Pre-filters — Volume spikes, Trend Template, RS, 52-week bands, etc.

Related MCP server: KIS MCP Server

🛠️ Tools

Tool	Description	Input Example
`get_stock_analysis`	Korean stock technical analysis	`ticker="005930"` (Samsung Electronics)
`get_us_stock_analysis`	US stock technical analysis	`symbol="NVDA"`
`search_stock`	Search stock name → stock code	`keyword="Alchera"`
`screen_kr_momentum`	🐎 Korean Catching the Running Horse (Stage 2 trend)	`market="ALL"`
`screen_us_momentum`	🐎 US Catching the Running Horse	`symbols=None` (Yahoo auto-seed)
`screen_kr_breakout`	🌱 Korean Finding the Horse About to Run (VCP/Accumulation/Late Stage 1)	`market="ALL"`
`screen_us_breakout`	🌱 US Finding the Horse About to Run	`symbols=None`
`diagnose_stock`	Strategy diagnosis for a specific stock	`ticker="005930", market="KR"`

🎯 Screening: Two Philosophies

🐎 Momentum — Catching the Running Horse

Captures Stage 2 continuation for stocks that have already entered an uptrend. Based on O'Neil's CANSLIM and Minervini's Trend Template theories.

Pipeline

시드 (네이버 거래량/상승률/급등  |  Yahoo most_actives/day_gainers/small_cap_gainers)
  ↓
① min_trade_value         — 유동성
② 당일 과열 제외 +10% 이상  — 추격매수 방지
③ 20일 내 거래량 급증 ≥ 3x  — 자금 유입 시그널
④ Minervini Trend Template — Stage 2 6조건 (ON)
⑤ 52주 고점 근접            — OFF (Trend Template과 중복)
⑥ RS vs 지수               — OFF (opt-in, 강한 종목만 보고 싶을 때)
  ↓
10가지 Momentum 전략 적용

Applied Strategies (10)

Existing 4: Golden Cross + Volume, Pullback Buy, Momentum Breakout, Volume Explosion
New 6: RSI Divergence, MACD Divergence, Stochastic, BB Squeeze, Ichimoku Breakout, 3-line Alignment

🌱 Breakout — Finding the Horse About to Run

Captures stocks that haven't moved significantly yet, in the accumulation phase / pre-breakout. Based on Mark Minervini's VCP pattern and Wyckoff accumulation theory.

Pipeline

시드 (Momentum과 동일 — 매집도 거래량에 반영됨)
  ↓
① min_trade_value
② 당일 과열 제외 +10% 이상
③ 누적 상승 한도: 최근 30일 +30% 이상 제외   ← Breakout 전용
④ 52주 밴드: 고점 × 0.85 이하 AND 저점 × 1.20 이상 ← 전용 (중간권만)
⑤ 20일 내 거래량 급증 ≥ 2x                    (momentum의 3x보다 완화)
  ↓
Breakout 7전략 적용  (Trend Template / 52w 근접 / RS 모두 off)

Applied Strategies (7)

Reused 4: Pullback Buy, Volume Explosion, MACD Divergence, BB Squeeze
New 3: VCP Volatility Contraction, Silent Accumulation, Late Stage 1 Transition

🧪 Comparison of the Two Modes

	🐎 Momentum	🌱 Breakout
Philosophy	Trend Continuation	Accumulation → Early Breakout
Cumulative Return	No limit	Exclude 30-day +30% or more
52-week Position	Near high recommended	Below 85% of high + Above 120% of low band
Trend Template	ON (Requires MA alignment)	OFF
Volume Spike	3.0x	2.0x (Accumulation is less explosive)
Strategy Count	10	7 (including 3 new)
Suitable Timing	Strong market, trend following	Post-correction re-entry, bottom reversal

Practical Result Comparison Example

Based on the same market (KOSPI):

Momentum: Perspect (meets 6 strategies) — A stock already running
Breakout: Daewon Cable 30-day -20.32%, pullback + VCP at 72% of 52-week high — Typical accumulation

📊 New Breakout Strategy Explanation

VCP (Volatility Contraction Pattern)

Divides the last 15 days into three 5-day segments to determine if the high-low range (%) sequentially contracts. Coiling spring shape → Breakout imminent. (Mark Minervini)

Silent Accumulation

Average volume of the last 20 days is higher than the previous 20 days with some spike days, but the price fluctuation range for the same 20 days is within ±8% → Hidden institutional accumulation.

Late Stage 1 Transition

Transition phase from a bottom box range (Stage 1) to a gentle rise (early Stage 2).

MA60 slope higher than 1 month ago
MA20 > MA60 (Short-term upward transition)
Close > MA60 (Support secured)
BB width ≤ 20-day average (Volatility not yet expanded)

🔎 Pre-filter Parameter Cheat Sheet

Momentum Screener Common

Parameter	Default	Purpose
`exclude_if_up_pct`	10.0	Exclude if up +10% today. `None` if not applied
`spike_threshold`	3.0	Volume spike multiplier
`enable_trend_template`	True	Minervini Trend Template
`enable_rs_filter`	False	RS filter (on to see only strong stocks)
`min_rs_outperformance`	0.0	Benchmark outperformance (pp) threshold

Breakout Screener Common

Parameter	Default	Purpose
`max_cumulative_return_pct`	30.0	Upper limit of cumulative return (%) for last N days
`cumulative_return_days`	30	Cumulative calculation period
`high_ceiling`	0.85	Pass only if below 52-week high × this value
`low_floor`	1.20	Pass only if above 52-week low × this value
`spike_threshold`	2.0	Volume spike (relaxed multiplier for accumulation)

📦 Installation

Prerequisites

Python 3.13+
uv (Recommended)

Setup

git clone https://github.com/Juuuuuuni/stock-mcp-server.git
cd stock-mcp-server
uv sync

🚀 Usage

Claude Desktop Integration

Add the following to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "stock-analyzer": {
      "command": "uv",
      "args": [
        "--directory",
        "/절대/경로/stock-mcp-server",
        "run",
        "python",
        "server.py"
      ]
    }
  }
}

Direct Execution

uv run python server.py

💬 Conversation Examples

Individual Stock Analysis

👤 삼성전자 최근 분석해줘
🤖 [get_stock_analysis("005930")] → 현재가 / RSI / MACD / 추세 해석

👤 NVDA 한 달 차트 분석
🤖 [get_us_stock_analysis("NVDA", days=30)]

👤 알체라 종목코드가 뭐야?
🤖 [search_stock("알체라")] → 347860

Screening (Running Horse)

👤 지금 코스피에서 뜨는 종목 찾아줘
🤖 [screen_kr_momentum(market="KOSPI")]
   → Stage 2 추세 + 거래량 급증 종목. 퍼스텍(6전략), 대우건설(3전략) …

👤 미국 주식에서 강세 종목만 (RS 10pp 이상)
🤖 [screen_us_momentum(enable_rs_filter=True, min_rs_outperformance=10.0)]

Screening (Horse About to Run)

👤 코스닥에서 매집 단계 종목 스크리닝
🤖 [screen_kr_breakout(market="KOSDAQ")]
   → 누적 상승 30% 미만 + 52주 중간권 + VCP/매집 패턴

👤 아직 안 오른 바닥 종목만 (최근 30일 +10% 이내)
🤖 [screen_kr_breakout(max_cumulative_return_pct=10.0)]

Individual Stock Strategy Diagnosis

👤 알체라 지금 어떤 단계야?
🤖 [diagnose_stock(ticker="347860", market="KR")]
   → 10전략 중 어느 조건 통과했는지 상세 진단

📋 Output Examples

Momentum Screening Results (Summary)

{
  "스크리닝일": "20260413",
  "대상시장": "KOSPI",
  "시드후보수": 80,
  "필터링_단계별_통과": {
    "당일과열제외": 64,
    "거래량급증": 31,
    "Trend_Template": 8,
    "52주고점근접": 0,
    "RS": 0
  },
  "필터링결과수": 26,
  "결과": [
    {
      "종목코드": "010820",
      "종목명": "퍼스텍",
      "전략": "모멘텀 돌파",
      "점수": "5/5",
      "현재가": 2340,
      "등락률": "+4.23%",
      "RSI": 68.4,
      "거래량비": "2.1x",
      "20일내_최대거래량배율": "8.7x",
      "복수전략": true
    }
  ]
}

Breakout Screening Results (Summary)

{
  "스크리닝일": "20260413",
  "모드": "Breakout (곧 달릴 말)",
  "대상시장": "KOSPI",
  "시드후보수": 80,
  "필터링_단계별_통과": {
    "당일과열제외": 64,
    "누적상승한도": 55,
    "52주밴드": 22,
    "거래량급증": 12
  },
  "필터링결과수": 28,
  "결과": [
    {
      "종목코드": "006340",
      "종목명": "대원전선",
      "전략": "눌림목 매수",
      "점수": "5/5",
      "현재가": 1245,
      "30일누적": "-20.32%",
      "52주고점대비": "72.2%",
      "52주저점대비": "128.4%",
      "복수전략": true
    }
  ]
}

🧩 Tech Stack

FastMCP — MCP server framework
pykrx — Korea Exchange data
yfinance — Yahoo Finance data
ta — Technical analysis indicators
BeautifulSoup + lxml — Naver Finance / Yahoo Screener HTML parsing
pandas — Data processing

📚 References

William J. O'Neil — How to Make Money in Stocks (CANSLIM)
Mark Minervini — Trade Like a Stock Market Wizard (Trend Template, VCP)
Richard Wyckoff — Price-Volume Accumulation/Distribution Theory
Stan Weinstein — Secrets for Profiting in Bull and Bear Markets (Stage Analysis)

📄 License

MIT

Available Tools

8 tools

diagnose_stockA

특정 종목이 10가지 단기 전략 중 어떤 조건에 해당하는지 상세 진단합니다.

■ 기존 전략: 골든크로스+거래량, 눌림목 매수, 모멘텀 돌파, 거래량 폭발 ■ 신규 전략: RSI 다이버전스, MACD 다이버전스, 스토캐스틱 과매수/과매도, BB 스퀴즈, 일목균형표 구름대 돌파, 3선 정배열/역배열

Args: ticker: 종목코드 (한국) 또는 티커심볼 (미국). 예: '005930', 'AAPL' market: 'KR' 또는 'US'. 기본 'KR'

Inputs: ticker (required), market. Returns: result

get_stock_analysisA

종목코드를 입력하면 OHLCV + 기술적 지표를 분석합니다.

Args: ticker: 종목코드 (예: '347860' for 알체라, '005930' for 삼성전자) days: 조회 기간 (일수, 기본 120일)

Inputs: ticker (required), days. Returns: result

get_us_stock_analysisC

미국 주식 종목을 분석합니다.

Args: symbol: 티커 심볼 (예: 'AAPL', 'TSLA', 'NVDA', 'GOOGL') days: 조회 기간 (일수, 기본 120일)

Inputs: symbol (required), days. Returns: result

screen_kr_breakoutA

한국 주식에서 '곧 달릴 말' — 매집/돌파 직전 단계 종목을 필터링합니다.

screen_kr_momentum과 반대 컨셉. 이미 크게 오른 종목을 배제하고 중간권에서 매집 중인 종목 / 변동성 수축 국면 / Stage 1 말기 종목을 찾습니다.

[시드] 네이버 거래량상위 + 상승률상위 + 급등 합집합 [사전필터] 순차 적용: · 거래대금 · 당일 과열 제외 (exclude_if_up_pct) · 최근 N일 누적 상승률 < max_cumulative_return_pct (아직 안 달림) · 52주 밴드 (고점 × high_ceiling 이하 AND 저점 × low_floor 이상) · 거래량 급증 (기본 2x — momentum의 3x보다 약해도 매집 시그널로 인정) [전략] Breakout 전용 7개

재사용: 눌림목 매수 · 거래량 폭발 · MACD 다이버전스 · BB 스퀴즈
신규: VCP 변동성 수축 · 조용한 매집 · Stage 1 말기 전환

Args: market: 'KOSPI' | 'KOSDAQ' | 'ALL' top_n: 시드 후보 상한 min_trade_value: 최소 거래대금(원) exclude_if_up_pct: 오늘 이 % 이상 오른 종목 제외 (None 미적용) max_cumulative_return_pct: 최근 N일 누적 상승률 상한(%) (기본 30) cumulative_return_days: 누적 상승률 계산 기간 (기본 30) high_ceiling: 52주 고점 대비 상한 비율 (0.85 = 고점의 85% 이하) low_floor: 52주 저점 대비 하한 비율 (1.20 = 저점의 120% 이상) lookback_days: 거래량 급증 룩백 spike_threshold: 거래량 급증 배율 (기본 2.0) baseline_days: 비교 기준 기간

Inputs: market, top_n, min_trade_value, exclude_if_up_pct, +7 more. Returns: result

screen_kr_momentumA

한국 주식에서 '최근 N일 내 거래량 급증 + 추세 정합' 종목을 필터링합니다.

[시드] 네이버 거래량상위 + 상승률상위 + 급등 합집합 [사전필터] 순차 적용: · 거래대금: min_trade_value 이상 · 당일 과열 제외: 오늘 등락률이 exclude_if_up_pct 이상이면 제외 (추격 매수 방지) · 거래량 급증: max(최근 lookback일) / 이전 baseline일 평균 ≥ spike_threshold · Minervini Trend Template (옵션): Stage 2 상승추세 6조건 · 52주 고점 근접 (옵션): 현재가 ≥ 52주고점 × high_proximity · RS vs KODEX 200 (옵션): 3개월 초과수익률 ≥ min_rs_outperformance (pp) [전략] 10가지 기술적 전략 적용

Args: market: 'KOSPI' | 'KOSDAQ' | 'ALL' top_n: 시드 후보 상한 min_trade_value: 최소 거래대금 필터(원) exclude_if_up_pct: 오늘 등락률이 이 값(%) 이상이면 제외. None이면 미적용 (기본 10.0) lookback_days: 거래량 급증 룩백 (기본 20) spike_threshold: 급증 배율 (기본 3.0) baseline_days: 비교 기준 기간 (기본 40) enable_trend_template: Minervini Trend Template 사용 여부 enable_near_52w_high: 52주 고점 근접 필터 사용 여부 high_proximity: 52주 고점 대비 허용 비율 (0.75 = 고점의 75% 이상) enable_rs_filter: KODEX 200 대비 RS 필터 사용 여부 rs_period_days: RS 수익률 계산 기간 (기본 63 ≈ 3개월) min_rs_outperformance: 벤치마크 초과수익 하한 (pp)

Inputs: market, top_n, min_trade_value, exclude_if_up_pct, +9 more. Returns: result

screen_us_breakoutA

미국 주식에서 '곧 달릴 말' — 매집/돌파 직전 단계 종목을 필터링합니다.

screen_us_momentum과 반대 컨셉. 이미 크게 오른 종목을 배제하고 중간권에서 매집 중인 종목 / 변동성 수축 국면 / Stage 1 말기 종목을 찾습니다.

[시드] symbols 미지정 시 Yahoo most_actives + day_gainers + small_cap_gainers [사전필터] KR breakout과 동일 구조 [전략] Breakout 전용 7개

Args: symbols: 스크리닝할 티커 목록. None이면 Yahoo 스크리너에서 시드 수집 top_n: 시드 후보 상한 exclude_if_up_pct: 오늘 이 % 이상 오른 종목 제외 max_cumulative_return_pct: 최근 N일 누적 상승률 상한 cumulative_return_days: 누적 상승률 계산 기간 high_ceiling: 52주 고점 대비 상한 (0.85 = 고점의 85% 이하) low_floor: 52주 저점 대비 하한 (1.20 = 저점의 120% 이상) lookback_days: 거래량 급증 룩백 spike_threshold: 거래량 급증 배율 (기본 2.0) baseline_days: 비교 기준 기간

Inputs: symbols, top_n, exclude_if_up_pct, max_cumulative_return_pct, +6 more. Returns: result

screen_us_momentumA

미국 주식에서 '최근 N일 내 거래량 급증 + 추세 정합' 종목을 필터링합니다.

[시드] symbols 미지정 시 Yahoo most_actives + day_gainers + small_cap_gainers [사전필터] 순차 적용: · 당일 과열 제외: 오늘 등락률이 exclude_if_up_pct 이상이면 제외 (추격 매수 방지) · 거래량 급증: max(최근 lookback일) / 이전 baseline일 평균 ≥ spike_threshold · Minervini Trend Template (옵션): Stage 2 상승추세 6조건 · 52주 고점 근접 (옵션): 현재가 ≥ 52주고점 × high_proximity · RS vs SPY (옵션): 3개월 초과수익률 ≥ min_rs_outperformance (pp) [전략] 10가지 기술적 전략 적용

Args: symbols: 스크리닝할 티커 목록. None이면 Yahoo 스크리너에서 시드 수집 top_n: 시드 후보 상한 exclude_if_up_pct: 오늘 등락률이 이 값(%) 이상이면 제외. None이면 미적용 (기본 10.0) lookback_days: 거래량 급증 룩백 spike_threshold: 급증 배율 baseline_days: 비교 기준 기간 enable_trend_template: Minervini Trend Template 사용 여부 enable_near_52w_high: 52주 고점 근접 필터 사용 여부 high_proximity: 52주 고점 대비 허용 비율 (0.75 = 고점의 75% 이상) enable_rs_filter: SPY 대비 RS 필터 사용 여부 rs_period_days: RS 수익률 계산 기간 (기본 63 ≈ 3개월) min_rs_outperformance: 벤치마크 초과수익 하한 (pp)

Inputs: symbols, top_n, exclude_if_up_pct, lookback_days, +8 more. Returns: result

search_stockA

종목명으로 종목코드를 검색합니다.

Args: keyword: 검색할 종목명 (예: '삼성전자', '알체라')

Inputs: keyword (required). Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored 2026-04-26 07:55 across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: diagnosis, analysis (KR/US), screening by strategy and market, and ticker search. There is no overlap between tools; even the screening tools are differentiated by market and strategy type.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., diagnose_stock, get_stock_analysis, screen_kr_breakout). The naming scheme is predictable and uniform across all tools.

Tool Count5/5

With 8 tools, the server is well-scoped for stock analysis and screening. It covers core functionalities without being overly numerous or too sparse, providing a focused yet comprehensive set.

Completeness4/5

The tool set covers analysis, diagnosis, screening for both markets, and ticker search. Minor gaps exist, such as the absence of a dedicated quote tool, but the analysis tools include OHLCV. Overall, the surface is thorough for its domain.

Resources

Related MCP Connectors

Daepak Market Intelligence
io.github.Mobiss11
Market analyst tools + AI agent: crypto, US equities, options, Korea, fundamentals, macro, backtests
Finance Cryptocurrency
1
https://daepak.com/mcp
cotrader
io.github.get-cotrader
Screen 11,000+ stocks using natural language and detect chart patterns via MCP.
Finance Search Research & Data
2
https://api.getcotrader.com/mcp
MarketCrew — live market data & stock analysisA
ai.marketcrew
Stock prices, charts & technical analysis for US stocks, ETFs and crypto. Read-only, no signup.
Finance Cryptocurrency
151
https://marketcrew.ai/mcp
technicalA
io.github.oswarld
Technical analysis (RSI, MA, signal score) for 9,400+ global stocks, by ticker or name.
Finance Research & Data
52
https://www.bullbear.ninja/api/mcp

Related MCP Servers

pykrx-mcpofficial
Finance Research & Data
sharebook-kr
A
license
Not graded
quality
D
maintenance
Provides Korean stock market data (KOSPI, KOSDAQ, KONEX) including prices, fundamentals, investor trading, short selling, and indices via MCP protocol, enabling natural language queries from AI agents like ChatGPT and Claude.
Updated 9 months ago (2026-02-01 02:52 UTC)
73 PyPI
3
MIT
KIS MCP Server
Finance Search
nangchang
F
license
A
quality
C
maintenance
Enables Claude to trade Korean and overseas stocks, check balances, and search stock information through the Korea Investment & Securities Open API.
Updated 18 days ago (2026-10-26 15:29 UTC)
12
-
Yahoo Finance MCP Server
Finance Search
danishashko
A
license
A
quality
B
maintenance
Provides real-time stock market data for Claude Desktop and MCP-compatible clients, enabling natural language queries for quotes, historical prices, company profiles, financial statements, analyst ratings, comparisons, news, options, holdings, dividends, estimates, symbol search, and market status.
Updated 6 days ago (2026-11-07 18:31 UTC)
18
2,227 npm
24
MIT
Finance MCP Server
Finance Research & Data
akshatbindal
A
license
Not graded
quality
D
maintenance
Provides comprehensive stock market data and technical analysis tools via the MCP protocol, enabling real-time quotes, historical data, and professional indicators like RSI and MACD for Claude Desktop and other clients.
Updated a year ago (2025-07-16 05:29 UTC)
26 PyPI
5
Apache 2.0