TradePilot MCP Server

TradePilot MCP Server

A production-grade MCP server that integrates Polygon.io market data with an 18-layer technical analysis engine to generate actionable options trading signals and high-probability playbooks.

Category
访问服务器

README

🚀 TradePilot MCP Server v3.0

Advanced 18-Layer Trading Intelligence Engine

A production-grade MCP (Model Context Protocol) server that combines Polygon.io real-time market data with an 18-layer technical analysis engine for autonomous options trading intelligence.


📊 What is This?

TradePilot is a FastAPI-based MCP server that:

  • Fetches real-time and historical market data from Polygon.io
  • Runs analysis through 18 specialized layers (Technical + Price Action + Options + Master Brain)
  • Provides 14 high-probability playbooks targeting 85-95% win rates
  • Delivers actionable options trading signals with precise strike/expiry recommendations
  • Includes multi-ticker scanning, risk management, and alert notifications

Think of it as your AI options trading copilot powered by institutional-grade analysis.


🎯 Key Features

  • 18-Layer Analysis System

    • Layers 1-10: Technical indicators (Momentum, Volume, Trend, Structure)
    • Layers 11-13: Price action (Support/Resistance, VWAP, Volume Profile)
    • Layers 14-17: Options analysis (IV, Greeks, Gamma, Put/Call ratios)
    • Layer 18: Master Brain with 14 playbooks
  • Trading Modes

    • SCALP: 0-2 DTE options
    • SWING: 7-45 DTE options
    • INTRADAY: Same-day trades
  • Advanced Features

    • Multi-ticker scanner with filtering
    • Kelly Criterion position sizing
    • Risk management with drawdown protection
    • Discord/Slack/Telegram alerts
    • Backtesting engine
    • AI-ready JSON output

🚀 Quick Start

# Clone the repository
git clone https://github.com/Sakhir786/tradepilot-mcp-server.git
cd tradepilot-mcp-server

# Set up environment
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Configure environment variables
cp .env.example .env
# Edit .env and add your POLYGON_API_KEY

# Run the server
python main.py
# Or with uvicorn:
uvicorn main:app --host 0.0.0.0 --port 10000

Access documentation at: http://localhost:10000/docs


📡 API Endpoints

18-Layer Analysis

  • GET /engine18/analyze - Full 18-layer analysis
  • GET /engine18/quick - Quick signal check
  • GET /engine18/scan - Multi-ticker scanner
  • GET /engine18/playbooks - List all 14 playbooks
  • GET /engine18/health - System health check

Market Data (Polygon.io)

  • GET /candles - OHLCV data
  • GET /options - Options chain
  • GET /news - Latest news
  • GET /ticker-details - Company info

🔧 Environment Variables

POLYGON_API_KEY=your_api_key_here
TRADEPILOT_PRODUCTION_PATH=/path/to/tradepilot-mcp-server
TRADEPILOT_LAYERS_PATH=/path/to/layers
TRADEPILOT_PORTFOLIO_VALUE=100000
TRADEPILOT_DISCORD_WEBHOOK=your_webhook_url

📊 Example Usage

import requests

# Full analysis
response = requests.get(
    "http://localhost:10000/engine18/analyze",
    params={"symbol": "SPY", "mode": "swing"}
)
analysis = response.json()

print(f"Direction: {analysis['analysis_summary']['direction']}")
print(f"Win Probability: {analysis['analysis_summary']['win_probability']}%")

🎯 14 High-Probability Playbooks

Bullish (CALLS):

  1. Liquidity Sweep + BOS (85-95%)
  2. CHoCH Reversal (82-92%)
  3. Trend Continuation (80-90%)
  4. FVG Fill + Rejection (81-88%)
  5. Order Block Bounce (79-87%)
  6. Divergence + Structure (80-88%)
  7. VWAP Reclaim (77-85%)

Bearish (PUTS): 8-14. Mirror patterns for bearish setups


🔐 Security & Best Practices

  • Never commit .env files
  • Keep API keys secure
  • Use environment variables for sensitive data
  • Enable rate limiting for production deployments

📝 License

MIT License - See LICENSE file for details


🤝 Contributing

Contributions welcome! Please open an issue or submit a pull request.


📧 Support

For issues or questions, please open a GitHub issue.

TradePilot v3.0 - Professional Options Trading Intelligence 🚀📈

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选