ezib-mcp

<h1 align="center">EZIB-MCP: Interactive Brokers Trading for AI Agents</h1> A [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server implementation that enables AI agents to interact with Interactive Brokers' trading platform, providing access to market data, account information, and trading functionality. ## Overview This project provides an MCP server built on `ezib_async` that allows AI agents to connect to Interactive Brokers, retrieve account information, manage portfolios, and execute trades. It serves as both a practical tool for algorithmic trading and a reference implementation for building MCP servers. The implementation follows the best practices laid out for building MCP servers, allowing seamless integration with any MCP-compatible client. ## Features The server provides several powerful tools for trading and market data: 1. **Account Information**: Access account balances, positions, and portfolio data 2. **Market Data**: Retrieve real-time and historical market data 3. **Order Management**: Place, modify, and cancel orders 4. **Position Management**: Monitor and manage trading positions ## Prerequisites - Python 3.11+ - Interactive Brokers TWS or IB Gateway running - Docker if running the MCP server as a container (recommended) ## Installation ### Using pip 1. Clone this repository: ```bash git clone https://github.com/kelvingao/ezib-mcp.git cd ezib-mcp ``` 2. Install dependencies: ```bash pip install -e . ``` 3. Create a `.env` file based on `.env.example`: ```bash cp .env.example .env ``` 4. Configure your environment variables in the `.env` file (see Configuration section) ### Using Docker (Recommended) 1. Build the Docker image: ```bash docker build -t mcp/ezib --build-arg PORT=8050 . ``` 2. Create a `.env` file based on `.env.example` and configure your environment variables ## Configuration The following environment variables can be configured in your `.env` file: | Var…