Trader Journal MCP
Provides AI-powered trading analytics and coaching by analyzing historical trades to identify strategies, emotional patterns, and behavioral mistakes via MCP tools.
README
Trader Journal MCP
AI-powered trading analytics and coaching platform built with FastAPI, SQLite, and MCP.
Overview
Trader Journal MCP helps traders discover their trading edge by analyzing historical trades and exposing insights through an MCP server that can be used by AI assistants.
Instead of only recording trades, the system identifies:
- Best-performing strategies
- Best-performing setups
- Emotional trading patterns
- Drawdown and recovery metrics
- Trading expectancy
- Risk-reward performance
- Behavioral mistakes such as revenge trading and overtrading
The ultimate goal is to provide an AI Trading Coach that helps traders improve decision-making based on real historical data.
Architecture
MT5 CSV ↓ Importer ↓ SQLite Database ↓ Analytics Engine ↓ FastAPI API ↓ MCP Server ↓ AI Assistant
Features
Performance Analytics
- Trading Summary
- Expectancy Analysis
- Risk-Reward Analysis
- Monthly Performance
- Drawdown Analysis
- Equity Curve
Behavioral Analytics
- Revenge Trading Detection
- Overtrading Detection
Context Analytics
- Pair Performance
- Session Performance
- Day of Week Analysis
- Trade Duration Analysis
- Strategy Performance
- Emotion Performance
- Setup Performance
- Strategy + Emotion Analysis
AI Trading Coach
The AI coach combines all analytics and identifies:
- Strongest trading edge
- Weakest trading behavior
- Best strategy
- Best setup
- Best emotional state
- Personalized recommendations
API Endpoints
Performance
- GET /api/v1/performance/summary
- GET /api/v1/performance/expectancy
- GET /api/v1/performance/risk-reward
- GET /api/v1/performance/drawdown
- GET /api/v1/performance/equity-curve
- GET /api/v1/performance/coach
Behavior
- GET /api/v1/behavior/revenge-trading
- GET /api/v1/behavior/overtrading
Context
- GET /api/v1/context/pairs
- GET /api/v1/context/sessions
- GET /api/v1/context/days
- GET /api/v1/context/duration
- GET /api/v1/context/strategies
- GET /api/v1/context/emotions
- GET /api/v1/context/setups
- GET /api/v1/context/monthly
- GET /api/v1/context/strategy-emotions
MCP Tools
Performance
- get_summary()
- get_expectancy()
- get_risk_reward()
- get_monthly_performance()
- get_drawdown_analysis()
- get_equity_curve()
Behavior
- detect_revenge_trading()
- detect_overtrading()
Context
- get_session_analysis()
- get_strategy_performance()
- get_emotion_performance()
- get_setup_performance()
- get_strategy_emotion_performance()
AI Coach
- analyze_my_edge()
Tech Stack
- Python
- FastAPI
- SQLite
- SQLAlchemy
- Pandas
- FastMCP
- HTTPX
Future Roadmap
- Live MT5 integration
- Automated trade journaling
- Equity curve visualizations
- AI trade reviews
- Trade screenshots
- RAG-powered trading memory
- Portfolio analytics
- Multi-account support
- Telegram integration
- Voice-based trading coach
Author
Cephars Bonacci
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。