MCP Catalogs
HomeQMT-MCP screenshot

QMT-MCP

by guangxiangdebizi·181·Score 45

QMT-MCP is a modular quantitative trading system integrating FastMCP with XTQuant for intelligent strategy generation and real-time trading execution.

financedeveloper-toolsai-llm
46
Forks
3
Open issues
10 mo ago
Last commit
2d ago
Indexed

Overview

QMT-MCP is a comprehensive MCP server that connects AI assistants to the XTQuant/QMT trading platform. It enables automated trading through tools for placing/canceling orders, generating strategies, and performing backtests. The system is built with a modular architecture supporting various trading strategies and risk control mechanisms. It features detailed API documentation, configuration options, and integration guides for different environments including Claude Desktop.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI assistant helping traders implement and execute quantitative strategies
you:Automating stock trading decisions based on generated signals
you:Backtesting trading strategies with performance metrics
you:What trading platforms are supported?
you:How can I customize risk control parameters?

When to choose this

Chinese traders using QMT/XTQuant platform who want AI-powered strategy generation and automated trading with risk controls.

When NOT to choose this

Traders using non-Chinese trading platforms, those requiring Windows compatibility, or those looking for open-source quant tools without vendor dependencies.

Tools this server exposes

4 tools extracted from the README
  • place_orderplace_order(symbol, quantity, price, direction)

    Execute stock trading order

  • cancel_ordercancel_order(order_id)

    Cancel a specified trading order

  • generate_ma_strategygenerate_ma_strategy(symbol, short_period, long_period, strategy_name)

    Generate a dual moving average trading strategy

  • save_qmt_strategysave_qmt_strategy(strategy_name, code)

    Save a custom QMT trading strategy

Comparable tools

pyalgotradevnpyrqalphabacktraderfastquant

Installation

Installation Steps

Requirements

  • Python 3.8+
  • XTQuant/QMT client (installed on Windows)

Setup

  1. Clone the repository
git clone https://github.com/guangxiangdebizi/QMT-MCP
cd QMT-MCP
  1. Install dependencies
pip install -r requirements.txt
  1. Create .env file with your configuration (see README for details)
  1. Start XTQuant client and ensure login
  1. Start the QMT-MCP server
python main.py

Claude Desktop Integration

Add to Claude Desktop configuration:

{
  "mcpServers": {
    "quantmcp": {
      "command": "python",
      "args": ["path/to/QMT-MCP/main.py"],
      "env": {
        "QMT_PATH": "your QMT installation path\userdata_mini"
      }
    }
  }
}

FAQ

What trading platforms are supported?
QMT-MCP supports XTQuant/Guojin QMT, a Chinese quantitative trading platform.
How can I customize risk control parameters?
Modify the MAX_ORDER_VALUE, MAX_POSITION_VALUE, and other parameters in the .env file.

Compare QMT-MCP with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.