NINX MCP Server
A Model Context Protocol (MCP) server that provides financial trading tools and market analysis capabilities, enabling AI assistants to access real-time market data, execute trades, analyze portfolios, and perform comprehensive financial analysis.
README
NINX MCP Server
A Model Context Protocol (MCP) server that provides financial trading tools and market analysis capabilities. This server enables AI assistants to access real-time market data, execute trades, analyze portfolios, and perform comprehensive financial analysis.
🚀 Features
Trading & Portfolio Management
- Binance Integration: Access account holdings, balances, and trading data
- Groww Integration: Complete trading platform with holdings, positions, orders, and margin data
- Portfolio Analysis: Comprehensive portfolio performance and risk assessment
- Real-time Market Data: Live prices, OHLC data, and market quotes
Market Analysis Tools
- Fundamental Analysis: Company financials, ratios, and valuation metrics
- Technical Analysis: RSI, MACD, Bollinger Bands, moving averages, and chart patterns
- Options Analysis: Greeks, implied volatility, and options strategies
- Market Overview: Sector performance, market trends, and news sentiment
- Stock Screening: Filter stocks based on various criteria
- Risk Assessment: Portfolio risk metrics and stress testing
📋 Prerequisites
- Node.js >= 22.x
- TypeScript (included in dependencies)
- API Keys for trading platforms:
- Binance API Key & Secret (optional)
- Groww API Key (optional)
🛠️ Installation
- Clone the repository:
git clone <repository-url>
cd nin-mcp-server
- Install dependencies:
npm install
- Set up environment variables:
cp config_env.example .env
Edit .env and add your API credentials:
# Binance API (optional)
BINANCE_API_KEY=your_binance_api_key
BINANCE_SECRET_KEY=your_binance_secret_key
# Groww API (optional)
GROWW_API_KEY=your_groww_api_key
🚀 Usage
Development Mode
npm run dev
Production Mode
npm start
Build
npm run build
Type Checking
npm run type-check
🔧 Available MCP Tools
Market Analysis
analyzeFundamentals(symbol)- Fundamental analysis for a stockanalyzeMarket(query)- Overall market conditions analysisanalyzeTechnicals(symbol)- Technical indicators and chart analysisanalyzeOptions(symbol)- Options chain and Greeks analysisgetMarketNews(query)- Latest market news and sentiment
Portfolio & Holdings
getUserHoldings()- Get user's portfolio holdingsgetUserBinanceHoldings()- Binance account holdingsanalyzePortfolio(holdings)- Portfolio performance analysis
Groww Platform Integration
getGrowwHoldings()- Groww portfolio holdingsgetGrowwPositions(segment?)- Positions datagetGrowwSymbolsLTP(symbols, segment?)- Last traded pricesgetGrowwSymbolsOHLC(symbols, segment?)- OHLC market datagetGrowwSymbolQuote(symbol, exchange?, segment?)- Detailed quotes
Trading Operations (Groww)
placeGrowwOrder(orderParams)- Place new ordersmodifyGrowwOrder(orderParams)- Modify existing orderscancelGrowwOrder(orderId, segment?)- Cancel ordersgetGrowwOrderStatus(orderId, segment?)- Order status
Margin & Risk
getGrowwUserMargin()- Available margingetGrowwOrderMargin(orders, segment?)- Calculate required margin
Stock Screening
screenStocks(criteria)- Filter stocks by criteria
🏗️ Project Structure
nin-mcp-server/
├── server/
│ ├── mcp-server-sdk.ts # Main MCP server implementation
│ ├── mcp-server.ts # Express server (legacy, not used)
│ └── manifest.ts # Server manifest
├── services/
│ ├── mcpService.ts # MCP service layer
│ └── mcpTools/ # Individual MCP tools
│ ├── fundamentalAnalysis.ts
│ ├── technicalAnalysis.ts
│ ├── portfolioAnalysis.ts
│ ├── marketAnalysis.ts
│ ├── optionsAnalysis.ts
│ ├── stockScreener.ts
│ ├── marketNews.ts
│ ├── riskAssessment.ts
│ ├── userHoldings.ts
│ ├── userBinanceHoldings.ts
│ ├── growwHoldings.ts
│ ├── growwPositions.ts
│ ├── growwLiveData.ts
│ ├── growwOrders.ts
│ ├── growwMargins.ts
│ └── index.ts
├── types/
│ └── mcp.ts # MCP type definitions
├── config_env.example # Environment variables template
└── package.json
🧪 Development
Code Formatting
# Check formatting
npm run format:check
# Auto-fix formatting
npm run format:write
Type Checking
npm run typecheck
🔒 Security
- Store API keys in environment variables, never in code
- Use
dotenvfor local development environment management - API keys are loaded securely from environment variables
📊 Integration with AI Assistants
This MCP server can be integrated with various AI assistants that support the Model Context Protocol:
Claude Desktop Configuration
- Copy the following configuration from your
config_env.examplefile - Add your actual API keys
- Update the file paths to match your installation
- Paste into Claude Desktop's MCP configuration
{
"mcpServers": {
"nin-terminal": {
"command": "ts-node",
"args": [
"/Users/YOUR_USERNAME/path/to/nin-mcp-server/server/mcp-server-sdk.ts"
],
"cwd": "/Users/YOUR_USERNAME/path/to/nin-mcp-server",
"env": {
"NINX_API_KEY": "your_actual_ninx_api_key",
"NINX_SECRET_KEY": "your_actual_ninx_secret_key",
"BINANCE_API_KEY": "your_actual_binance_api_key",
"BINANCE_SECRET_KEY": "your_actual_binance_secret_key",
"GROWW_API_KEY": "your_actual_groww_api_key"
}
}
}
}
Other MCP-Compatible Clients
For other MCP clients, use the stdio transport protocol with similar configuration, adjusting the format as needed for your specific client.
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Run tests and type checking
- Submit a pull request
📄 License
MIT License - see LICENSE file for details
🆘 Support
For issues and questions:
- Check the existing issues
- Create a new issue with detailed description
- Include logs and environment information
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。