Interactive Brokers MCP Server

Interactive Brokers MCP Server

Connects AI assistants to Interactive Brokers for intelligent portfolio management, options analysis, risk monitoring, and automated trading strategy suggestions. Enables real-time account tracking, Greeks calculations, option chain analysis, and playbook-based risk adjustments through natural language.

Category
访问服务器

README

ibkr-mcp

Interactive Brokers MCP Server for AI-powered trading assistance.

A Model Context Protocol (MCP) server that connects AI assistants to Interactive Brokers, enabling intelligent portfolio management, options analysis, and risk monitoring.

Features

  • Account Management: Real-time account summary, portfolio positions, and P&L tracking
  • Options Analysis: Option chain fetching, Greeks calculation, and strategy scanning
  • Risk Monitoring: Portfolio risk evaluation with configurable limits and alerts
  • Trading Strategies: Built-in support for covered calls, iron condors, PMCC, vertical spreads
  • News Integration: Historical news retrieval for market research
  • Playbook Actions: Automated adjustment suggestions based on risk rules

Installation

pip install ibkr-mcp

Prerequisites

  • Python 3.12+
  • Interactive Brokers TWS or IB Gateway running
  • Valid IBKR account credentials

Configuration

Set environment variables or create a .env file:

# IBKR Connection
IBKR_HOST=127.0.0.1
IBKR_PORT=4001          # TWS: 7497, IB Gateway: 4001
IBKR_CLIENT_ID=0
IBKR_ACCOUNT=           # Optional: specific account ID

# Optional: Data directories
IBKR_MCP_OPTION_DATA_DIR=optiondata
IBKR_MCP_OPTION_HISTORY_DIR=historydata
IBKR_MCP_MARKET_DATA_TYPE=LIVE  # LIVE, FROZEN, DELAYED, DELAYED_FROZEN

Usage

As MCP Server

Add to your Claude Desktop or other MCP-compatible client configuration:

{
  "mcpServers": {
    "ibkr-mcp": {
      "command": "uvx",
      "args": [
        "ibkr-mcp"
      ],
      "env": {
        "IBKR_ACCOUNT": "U1234567"
      }
    }
  }
}

Available Tools

Tool Description
get_account_summary Retrieve account summary for specific or all accounts
get_portfolio Get portfolio positions with P&L
get_positions Get normalized positions across accounts
get_greeks_summary Calculate portfolio Greeks (delta, gamma, theta, vega)
get_option_chains Fetch option chain snapshots
scan_option_signals Scan for options strategy trade signals
evaluate_portfolio_risk Evaluate risk against configured limits
generate_playbook_actions Generate adjustment suggestions
get_historical_news Retrieve historical news for symbols

Example Queries

Once connected through an AI assistant, you can ask:

  • "What's my current account balance and buying power?"
  • "Show me all my positions with Greeks"
  • "What's the option chain for AAPL expiring next month?"
  • "Evaluate my portfolio risk and suggest adjustments"
  • "Find covered call opportunities in my portfolio"

Risk Configuration

Create a risk.yaml file to define risk limits:

limits:
  max_delta: 100
  max_theta: -500
  max_concentration: 0.25

roll_rules:
  min_dte: 7
  target_delta: 0.30

Support

For issues and feature requests, please contact the maintainers.

License

Proprietary - All rights reserved.

Disclaimer

This software is for informational purposes only. It does not constitute financial advice. Trading involves substantial risk of loss. Use at your own risk.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选