maverick-mcp MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

maverick.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

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

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add maverick -- uvx maverick-mcp

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: maverick-mcp

Run a technical analysis check on a stock

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

Wann einsetzen: Before taking a position, you want indicators without opening TradingView.

Voraussetzungen

TIINGO_API_KEY — tiingo.com — free tier covers casual use

Ablauf

Pull full technicals

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

→ Tech dashboard
Interpret in plain English

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

→ Opinion with reasoning
Sanity check

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

→ Honest self-critique

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

Fallstricke

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

Kombinieren mit: yahoo-finance

Screen for candidates using Maverick screens

👤 Traders looking for setups ⏱ ~20 min intermediate

Wann einsetzen: Weekly or daily screen for fresh ideas.

Ablauf

Run the screen

Run get_maverick_stocks — what's passing today?✓ Kopiert

→ Candidate list
Triage

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

→ Ranked list with reasons

Ergebnis: A short watchlist derived from consistent criteria.

Backtest a strategy idea

👤 Strategy developers wanting quick feedback ⏱ ~25 min advanced

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

Ablauf

Run a backtest

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

→ Return stats + drawdown
Compare to baseline

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

→ Head-to-head

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

Analyze your paper portfolio

👤 Long-term investors ⏱ ~20 min intermediate

Wann einsetzen: Quarterly review: diversification, correlation, risk.

Ablauf

Build portfolio

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

→ Portfolio object
Correlation + risk

portfolio_correlation_analysis and risk_adjusted_analysis.✓ Kopiert

→ Matrix + stats
Recommendations

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

→ Diversification advice

Ergebnis: Actionable rebalancing ideas with justification.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert

maverick + notion

Save research memos to Notion

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

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

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

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Env vars: TIINGO_API_KEY, OPENROUTER_API_KEY, etc.

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

Niemals gewähren: 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.

Fehlerbehebung

Häufige Fehler und Lösungen

TIINGO_API_KEY missing

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

Prüfen: 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.

Prüfen: redis-cli ping

Alternativen

maverick-mcp vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen