MCP Server Shioaji

🚀 Shioaji's MCP Server

A server implementing the Model Context Protocol (MCP), enabling AI assistants to access the Shioaji trading API for the Taiwan financial market.

🚀 Quick Start

This server supports the Shioaji API functions through the MCP protocol, allowing AI models to:

• Obtain current stock prices
• Retrieve historical data
• List available stocks
• And more...

📦 Installation

Prerequisites

• Python 3.10 or higher
• uv (Fast Python package manager)

Using uv

uv sync

Configuration

Before running the server, you need to configure the Shioaji API credentials. There are two methods:

Environment Variables

Set the following environment variables:

export SHIOAJI_API_KEY="Your API Key"
export SHIOAJI_SECRET_KEY="Your Secret Key"

Using a .env File

Create a .env file in the root directory with the following content:

SHIOAJI_API_KEY=Your API Key
SHIOAJI_SECRET_KEY=Your Secret Key

Running the Server

Start the server using the following command:

uv run mcp-server-shioaji

The server will run on http://0.0.0.0:8000 by default.

💻 Usage Examples

Basic Usage

The server provides the following tools through MCP:

get_stock_price

Retrieve the current price based on the stock symbol.

{
  "tool": "get_stock_price",
  "params": {
    "symbols": "TW.2330,TW.2317"
  }
}

The response will contain price information for the requested stocks, including the opening price, high price, low price, closing price, trading volume, and other trading data.

get_kbars

Retrieve the K-line (candlestick) data for a stock within a specified date range.

{
  "tool": "get_kbars",
  "params": {
    "symbol": "TW.2330",
    "start_date": "2023-12-01",
    "end_date": "2023-12-15"
  }
}

If start_date is not provided, it defaults to today. If end_date is not provided, it defaults to the same as start_date.

scan_stocks

Scan stocks based on different ranking criteria.

{
  "tool": "scan_stocks",
  "params": {
    "scanner_type": "VolumeRank"
  }
}