IBKR MCP Server
Enables algorithmic trading with Interactive Brokers, including market data, order management, and risk analysis, with special support for 0DTE SPX options.
README
IBKR MCP Server
A comprehensive Model Context Protocol (MCP) server for Interactive Brokers TWS API integration, designed for algorithmic trading with a focus on 0DTE SPX options.
🚀 Features
Market Data
- Real-time stock quotes with bid/ask spreads
- Option chain retrieval with Greeks (Delta, Gamma, Theta, Vega)
- Index quotes (SPX, NDX, VIX)
- Historical price data for analysis
Order Management
- Market Orders: Immediate execution at best price
- Limit Orders: Execute at specified price or better
- Stop Orders: Trigger orders at stop price
- Bracket Orders: Entry + Take Profit + Stop Loss
- Trailing Stop Orders: Dynamic stop that follows price
- Manual/Auto Transmission: Option for TWS confirmation
Account Management
- Portfolio positions with P&L tracking
- Account summary (Net Liquidation, Cash, Buying Power)
- Real-time order status tracking
- Execution reports with commissions
Risk Management
- Position sizing tools
- Risk/reward calculation for brackets
- Greeks analysis for options
- Idempotent order submission
📋 Prerequisites
-
Interactive Brokers Account
- Active IB account (Paper or Live)
- TWS or IB Gateway installed
-
TWS Configuration
- Enable API connections in TWS
- Configure socket port (7497 for paper, 7496 for live)
- Set "Read-Only API" to unchecked for trading
-
Python Environment
- Python 3.9 or higher
- MCP-compatible environment (Claude Desktop)
🔧 Installation
1. Clone Repository
git clone https://github.com/yourusername/ibkr-mcp-server.git
cd ibkr-mcp-server
2. Create Virtual Environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
3. Install Dependencies
pip install -r requirements.txt
4. Configure Claude Desktop
Add to Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"ibkr": {
"command": "python",
"args": [
"C:/path/to/ibkr-mcp-server/src/ibkr_mcp_server.py"
]
}
}
}
🎯 Usage Examples
Connect to TWS
# Paper trading
ibkr_connect(mode="paper")
# Live trading
ibkr_connect(mode="live")
Get Market Data
# Stock quote
ibkr_get_stock_quote(symbol="SPY")
# Option chain for 0DTE SPX
ibkr_get_option_chain(underlying="SPX", include_greeks=True)
Place Orders
# Market order
ibkr_place_market_order(
symbol="SPY",
action="BUY",
quantity=100,
transmit=True
)
# Limit order
ibkr_place_limit_order(
symbol="AAPL",
action="BUY",
quantity=50,
limit_price=175.50
)
# Bracket order for 0DTE options
ibkr_place_bracket_order(
symbol="SPX",
sec_type="OPT",
action="BUY",
quantity=1,
entry_price=10.00,
take_profit_price=15.00, # +50% target
stop_loss_price=7.00 # -30% stop
)
Account Information
# Get positions
ibkr_get_positions()
# Get account summary
ibkr_get_account_summary()
# Check order status
ibkr_get_order_status(order_id=123)
🛠️ Available Tools
| Tool | Description |
|---|---|
ibkr_connect |
Connect to TWS/IB Gateway |
ibkr_disconnect |
Disconnect from TWS |
ibkr_get_connection_status |
Check connection status |
ibkr_get_stock_quote |
Get real-time stock quote |
ibkr_get_option_chain |
Get option chain with Greeks |
ibkr_place_market_order |
Place market order |
ibkr_place_limit_order |
Place limit order |
ibkr_place_bracket_order |
Place bracket order |
ibkr_cancel_order |
Cancel pending order |
ibkr_get_order_status |
Get order status |
ibkr_get_positions |
Get current positions |
ibkr_get_account_summary |
Get account metrics |
ibkr_get_historical_data |
Get historical bars |
ibkr_server_info |
Get server information |
🎮 TWS Setup Guide
1. Enable API Access
- Open TWS
- Go to File → Global Configuration
- Select API → Settings
- Enable Enable ActiveX and Socket Clients
- Configure port:
- Paper: 7497
- Live: 7496
- Optional: Set Master API client ID to "0"
2. Security Settings
- Under API → Precautions:
- Uncheck Read-Only API for trading
- Set Bypass Order Precautions based on preference
- Add trusted IP: 127.0.0.1
3. Market Data Subscriptions
Ensure you have appropriate market data subscriptions:
- US Stocks (Network A/B)
- Options (OPRA)
- Index data (for SPX)
📊 0DTE Trading Workflow
Example 0DTE SPX Strategy
# 1. Connect
ibkr_connect(mode="paper")
# 2. Get SPX price
spx_quote = ibkr_get_stock_quote(symbol="SPX")
# 3. Get 0DTE options (today's expiry)
options = ibkr_get_option_chain(
underlying="SPX",
strike_range=(5500, 5600), # Near ATM
include_greeks=True
)
# 4. Place bracket order on selected option
ibkr_place_bracket_order(
symbol="SPX",
sec_type="OPT",
action="BUY",
quantity=1,
entry_price=8.50,
take_profit_price=12.75, # +50% target
stop_loss_price=5.95 # -30% stop
)
# 5. Monitor position
ibkr_get_positions()
🔒 Security Considerations
- API Credentials: Never hardcode credentials
- Paper vs Live: Always test in paper first
- Order Validation: Use
transmit=Falsefor manual review - Position Limits: Implement position sizing rules
- Rate Limiting: Respect IB API rate limits
🐛 Troubleshooting
Connection Issues
Error: Failed to connect to TWS
Solution:
- Verify TWS is running
- Check API settings enabled
- Confirm correct port (7497/7496)
- Check firewall settings
No Market Data
Error: No market data available
Solution:
- Verify market data subscriptions
- Check if market is open
- Ensure proper contract specification
Order Rejected
Error: Order rejected - insufficient buying power
Solution:
- Check account balance
- Verify position limits
- Review margin requirements
📈 Performance Tips
- Connection Management: Keep persistent connection
- Data Caching: Cache frequently used data
- Batch Operations: Group related requests
- Error Handling: Implement retry logic
- Logging: Enable detailed logging for debugging
📝 License
MIT License - See LICENSE file for details
🤝 Contributing
Contributions welcome! Please read CONTRIBUTING.md
📧 Support
For issues and questions:
- GitHub Issues: Create Issue
- IB API Docs: Official Documentation
🏗️ Roadmap
- [ ] Advanced order types (OCO, Conditional)
- [ ] Options strategies (Spreads, Straddles)
- [ ] Real-time P&L tracking
- [ ] Risk analytics dashboard
- [ ] Backtesting integration
- [ ] Machine learning signals
⚠️ Disclaimer
This software is for educational purposes. Trading involves substantial risk of loss. Past performance does not guarantee future results. Always test thoroughly in paper trading before using with real funds.
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。