Angel One MCP Server
Provides comprehensive trading and market data functionality for Indian equity markets through Angel One's SmartAPI, enabling portfolio management, order placement, and real-time data queries.
README
Angel One MCP Server
Angel One Limited (formerly Angel Broking Limited) is India's leading stockbroker firm established in 1996, serving over 24.7 million clients across major Indian stock exchanges including BSE and NSE. This server provides access to Indian equity markets, commodities, and derivatives trading.
A Model Context Protocol (MCP) server that provides comprehensive trading and market data functionality for Angel One through their SmartAPI.
Features
Portfolio Management
- View stock holdings and investment portfolio
- Get comprehensive family account holdings
- Check current trading positions
- Access Risk Management System (RMS) limits
Trading Operations
- Place buy/sell orders (market, limit, stop-loss)
- Modify existing orders
- Cancel orders
- View order book and trade history
- Create GTT (Good Till Triggered) rules
Market Data
- Real-time Last Traded Price (LTP)
- Historical candlestick (OHLC) data
- Search for stocks and instruments
- Top gainers/losers analysis
- Put-Call Ratio (PCR) for market sentiment
Advanced Features
- Option Greeks calculation
- Position conversion
- Brokerage estimation
- Automated authentication with TOTP
- Comprehensive error handling
- Safety controls and dry-run mode
Installation
Development Installation (Current)
# Clone the repository
git clone https://github.com/YOUR_USERNAME/angel-one-mcp-server.git
cd angel-one-mcp-server
# Install dependencies
pip install -r requirements.txt
# Install in development mode
pip install -e .
PyPI Installation (Coming Soon)
pip install angel-one-mcp
Configuration
You can configure your Angel One credentials using either of these approaches:
Option 1: Environment Variables (Recommended)
Create a .env file in your project directory:
ANGEL_ONE_API_KEY=your_api_key
ANGEL_ONE_CLIENT_CODE=your_client_code
ANGEL_ONE_PASSWORD=your_password
ANGEL_ONE_TOTP_SECRET=your_totp_secret
MAX_ORDER_QUANTITY=10000
DRY_RUN_MODE=false
Then configure Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"angel-one-trading": {
"command": "python",
"args": ["-m", "angel_one_mcp.server"]
}
}
}
Option 2: Direct Configuration
Configure credentials directly in Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"angel-one-trading": {
"command": "python",
"args": ["-m", "angel_one_mcp.server"],
"env": {
"ANGEL_ONE_API_KEY": "your_api_key",
"ANGEL_ONE_CLIENT_CODE": "your_client_code",
"ANGEL_ONE_PASSWORD": "your_password",
"ANGEL_ONE_TOTP_SECRET": "your_totp_secret"
}
}
}
}
Note: Option 1 is recommended as it keeps sensitive credentials separate from configuration files.
Usage Examples
Portfolio Management
- "Show my current holdings"
- "What's my available margin?"
- "Display my open positions"
Trading
- "Buy 100 shares of RELIANCE at market price"
- "Place a limit order to sell 50 TCS at ₹3500"
- "Cancel order ID 12345"
Market Data
- "What's the current price of NIFTY?"
- "Show me top gainers today"
- "Get historical data for SBIN"
Security Features
- Automatic TOTP-based authentication
- Configurable order quantity limits
- Dry-run mode for testing
- Comprehensive error handling
- No credential storage in memory
Requirements
- Python 3.8+
- Angel One SmartAPI account
- Valid API credentials and TOTP setup
License
MIT License
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。