maverick-mcp MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

39+ tools across analysis, portfolio, screening, research, backtesting
VectorBT backtesting engine with 15+ prebuilt strategies
Pre-seeded DB of 520 S&P 500 stocks with screening recommendations
Optional Redis cache for 7-256x speedup on repeated queries
Supports STDIO, HTTP, SSE transports

라이브 데모

실제 사용 모습

maverick.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "maverick": {
      "command": "uvx",
      "args": [
        "maverick-mcp"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "maverick": {
      "command": "uvx",
      "args": [
        "maverick-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "maverick": {
      "command": "uvx",
      "args": [
        "maverick-mcp"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "maverick": {
      "command": "uvx",
      "args": [
        "maverick-mcp"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "maverick",
      "command": "uvx",
      "args": [
        "maverick-mcp"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "maverick": {
      "command": {
        "path": "uvx",
        "args": [
          "maverick-mcp"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add maverick -- uvx maverick-mcp

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: maverick-mcp

Run a technical analysis check on a stock

👤 DIY traders, chart-pattern students ⏱ ~10 min intermediate

언제 쓸까: Before taking a position, you want indicators without opening TradingView.

사전 조건

TIINGO_API_KEY — tiingo.com — free tier covers casual use

흐름

Pull full technicals

Run get_full_technical_analysis on TSLA. RSI, MACD, key moving averages, support/resistance.✓ 복사됨

→ Tech dashboard
Interpret in plain English

Is this bullish, bearish, or neutral right now? Be specific about conviction.✓ 복사됨

→ Opinion with reasoning
Sanity check

What assumptions could be wrong? Where's the thesis most fragile?✓ 복사됨

→ Honest self-critique

결과: A reasoned technical view you can double-check against your own judgment.

함정

Technicals alone are not a strategy — Cross-check against fundamentals and news before acting
Backtest overfitting — Always validate on out-of-sample data

함께 쓰기: yahoo-finance

Screen for candidates using Maverick screens

👤 Traders looking for setups ⏱ ~20 min intermediate

언제 쓸까: Weekly or daily screen for fresh ideas.

흐름

Run the screen

Run get_maverick_stocks — what's passing today?✓ 복사됨

→ Candidate list
Triage

For the top 10, get_full_technical_analysis each and rank by setup quality.✓ 복사됨

→ Ranked list with reasons

결과: A short watchlist derived from consistent criteria.

Backtest a strategy idea

👤 Strategy developers wanting quick feedback ⏱ ~25 min advanced

언제 쓸까: You have an idea like 'RSI cross above 50 with price above 200DMA' and want to see it on historical data.

흐름

Run a backtest

run_backtest: RSI-cross-above-50 + price>200DMA, SPY, 2015-2024, 10bps slippage.✓ 복사됨

→ Return stats + drawdown
Compare to baseline

compare_strategies: my strategy vs buy-and-hold SPY, same period.✓ 복사됨

→ Head-to-head

결과: Data-grounded view of whether an idea has legs.

Analyze your paper portfolio

👤 Long-term investors ⏱ ~20 min intermediate

언제 쓸까: Quarterly review: diversification, correlation, risk.

흐름

Build portfolio

portfolio_add_position for AAPL, MSFT, JNJ, VTI, GLD at current weights.✓ 복사됨

→ Portfolio object
Correlation + risk

portfolio_correlation_analysis and risk_adjusted_analysis.✓ 복사됨

→ Matrix + stats
Recommendations

What's overlapping? Where's concentration risk?✓ 복사됨

→ Diversification advice

결과: Actionable rebalancing ideas with justification.

조합

다른 MCP와 조합해 10배 효율

maverick + yahoo-finance

Pair maverick's technicals with Yahoo's raw fundamentals

Get maverick technical analysis on TSLA, plus Yahoo financial statements, and synthesize a thesis.✓ 복사됨

maverick + notion

Save research memos to Notion

Run research_comprehensive on AVGO; save the output as a Notion page under Investing / Research.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
fetch_stock_data	ticker, start, end, interval?	Base data fetch	1 Tiingo call
get_full_technical_analysis	ticker: str	One-stop technical view	multiple calls
get_maverick_stocks	(none)	Weekly screening	free (pre-seeded DB)
run_backtest	strategy, ticker, start, end, params	Validate a strategy idea	CPU-bound
portfolio_add_position	ticker, shares, cost_basis	Track holdings	free
portfolio_correlation_analysis	(none)	Diversification check	CPU
research_comprehensive	ticker: str	Deep dive; more expensive	LLM + web search calls
analyze_market_sentiment	ticker or sector	Context beyond price	web search calls

비용 및 제한

운영 비용

API 쿼터: Tiingo free tier: 500 req/hr, 50k/mo. Depends on OPENROUTER/Anthropic keys if used for research.
호출당 토큰: Simple data: 500-2000. research_comprehensive: 10k+
금액: Free tier covers hobbyist use; paid data + LLM keys for heavy research
팁: Enable Redis caching to avoid repeated Tiingo hits; OpenRouter saves 40-60% on LLM calls vs direct Anthropic.

보안

권한, 시크릿, 파급범위

자격 증명 저장: Env vars: TIINGO_API_KEY, OPENROUTER_API_KEY, etc.

데이터 외부 송신: Calls to Tiingo, Yahoo (via yfinance), FRED, plus whichever LLM/search keys you configure

절대 부여 금지: Exposing the HTTP transport to the public internet

This is personal research software — not investment advice, no audit trail suitable for fiduciary use.
Paper-trade results do not guarantee live performance.

문제 해결

자주 발생하는 오류와 해결

TIINGO_API_KEY missing

Create a free account at tiingo.com and set the env var.

확인: echo $TIINGO_API_KEY

Backtest hangs

VectorBT is CPU-bound; long histories on minute bars can take 10+ min. Narrow the date range or use daily bars.

Redis not connecting

Redis is optional; unset REDIS_HOST to fall back to in-memory cache.

확인: redis-cli ping

대안

maverick-mcp 다른 것과 비교

대안	언제 쓰나	단점/장점
yahoo-finance-mcp	You only need raw data and no technicals/backtest	No screens, no backtest, no portfolio
QuantConnect Lean / Zipline	You need institution-grade backtesting	No MCP; steeper setup
TradingView	You want a chart UI	Not programmatic; not MCP

maverick-mcp