IBKR TWS MCP Server
Enables LLM clients to interact with Interactive Brokers Trader Workstation for automated trading workflows. Supports market data retrieval, portfolio management, and order execution through the TWS API.
README
IBKR TWS MCP Server
This project implements a Model Context Protocol (MCP) server for the Interactive Brokers (IBKR) Trader Workstation (TWS) API. It uses the official modelcontextprotocol/python-sdk and ib_async to expose key TWS functionalities as MCP tools, enabling seamless integration with LLM clients for automated financial workflows, such as portfolio rebalancing.
The server supports the Streamable HTTP transport and is designed to be easily containerized using Docker.
Features
- MCP Compliance: Built with FastMCP for full adherence to the Model Context Protocol.
- Asynchronous TWS Integration: Leverages
ib_async(maintained fork of ib-insync) for non-blocking, asynchronous interaction with the TWS API. - Comprehensive Toolset: Exposes tools for connection management, market data retrieval (historical and streaming), account and portfolio querying, and order management (placing and canceling orders).
- Streaming Support: Implements Server-Sent Events (SSE) for real-time market data and account updates.
- Containerized Deployment: Ready-to-use Docker and Docker Compose configuration.
Getting Started
Please refer to the Setup Guide for detailed instructions on prerequisites, environment configuration, and running the server locally or in a container.
API Reference
A complete list of all exposed MCP tools, their parameters, and return types can be found in the API Reference.
End-to-End Testing
The server is designed to support the portfolio rebalancing E2E case. You can test all functionalities using the Claude MCP Inspector.
See the dedicated section in the API Reference for a step-by-step guide on how to use the Inspector to interact with your running server.
Project Structure
For a detailed explanation of the project organization, see PROJECT_STRUCTURE.md.
ibkr-tws-mcp-server/
├── src/ # Source code
│ ├── server.py # FastMCP server and tool definitions
│ ├── tws_client.py # TWS client wrapper using ib_async
│ └── models.py # Pydantic data models
├── tests/ # Test suite
│ ├── unit/ # Unit tests with mocks
│ └── integration/ # Integration test documentation
├── docs/ # Documentation
│ ├── API.md # MCP tools API reference
│ ├── SETUP.md # Setup and deployment guide
│ └── ... # Additional guides and troubleshooting
├── diagnostics/ # Diagnostic and testing scripts
├── scripts/ # Utility scripts
├── main.py # Application entry point
├── pyproject.toml # Project dependencies
└── README.md # This file
Documentation
- Setup Guide - Installation and configuration
- API Reference - Complete tool documentation
- Design Document - Architecture and design decisions
- Project Structure - Detailed project organization
- Migration Guide - ib-insync to ib_async migration
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。