fintools-mcp
Provides a comprehensive financial analysis toolkit for AI assistants, featuring technical indicators, options chain analysis, and risk-based position sizing. It enables users to perform stock market analysis and evaluate trade performance using real-time data from Yahoo Finance.
README
fintools-mcp
Financial analysis tools for AI assistants via MCP (Model Context Protocol).
Give Claude, ChatGPT, Cursor, or any MCP-compatible AI access to real financial analysis — not just stock prices, but the analytical toolkit a trader actually uses.
Tools
| Tool | What it does |
|---|---|
get_technical_indicators |
RSI, MACD, ATR, EMAs (9/21/50/200), Fibonacci levels, trend assessment |
get_stock_quote |
Current price, volume, 52-week range, market cap |
analyze_options_chain |
Options chain with IV analysis, liquidity filtering, put/call ratios |
calculate_position_size |
Risk-based position sizing with stop loss and profit target |
calculate_atr_position |
ATR-based position sizing — auto-calculates stop and target from volatility |
analyze_trades |
Win rate, profit factor, Sharpe ratio, drawdown, streaks from trade P&Ls |
compare_tickers |
Side-by-side technical comparison across multiple symbols |
Quick Start
Install
pip install fintools-mcp
Or with uv:
uv pip install fintools-mcp
Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"fintools": {
"command": "uv",
"args": ["run", "--from", "fintools-mcp", "fintools-mcp"]
}
}
}
Or if installed via pip:
{
"mcpServers": {
"fintools": {
"command": "fintools-mcp"
}
}
}
Add to Claude Code
claude mcp add fintools -- uv run --from fintools-mcp fintools-mcp
Examples
Once configured, you can ask your AI assistant things like:
- "What's the technical setup on AAPL right now?"
- "Analyze the SPY options chain for next Friday"
- "If I want to go long NVDA with a $100k account risking 1.5%, how many shares and where's my stop?"
- "Compare AAPL, GOOGL, MSFT, and AMZN — which has the strongest trend?"
- "Here are my last 20 trades: [150, -80, 200, ...] — what's my win rate and Sharpe?"
Example Output
Technical Indicators
> "What's the technical setup on SPY?"
SPY @ $573.42
RSI(14): 58.3 — bullish momentum
MACD: 2.14 (histogram +0.38, bullish)
ATR(14): $7.82
EMAs: 9 > 21 > 50 > 200 (fully stacked bullish)
Fibonacci: In golden pocket (0.618-0.65 retracement)
Trend: Bullish (all signals aligned)
Position Sizing
> "Size a long position on AAPL at $227, stop $220, target $245"
Shares: 214
Position value: $48,578
Risk: $1,498 (1.5% of $100k)
Reward: $3,852
R:R ratio: 2.57
Architecture
fintools-mcp/
├── fintools_mcp/
│ ├── server.py # MCP server — tool definitions
│ ├── data.py # Market data via yfinance
│ ├── indicators/ # Technical indicators (standalone, no deps)
│ │ ├── rsi.py # RSI — Wilder's smoothing
│ │ ├── macd.py # MACD (12, 26, 9)
│ │ ├── atr.py # ATR — Average True Range
│ │ ├── ema.py # EMA — any period
│ │ ├── vwap.py # VWAP — intraday, daily reset
│ │ └── fibonacci.py # Fibonacci retracement + golden pocket
│ └── analysis/
│ ├── position_sizer.py # Risk-based + ATR-based sizing
│ └── trade_stats.py # KPI calculator (60+ metrics)
└── tests/
Data Sources
- Stock data: Yahoo Finance (free, no API key required)
- Options data: Yahoo Finance options chains
- No API keys needed for basic functionality.
Development
git clone https://github.com/slimbiggins007/fintools-mcp.git
cd fintools-mcp
uv sync
uv run python -m fintools_mcp # starts the MCP server
Run tests:
uv run pytest
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。