QMT-MCP-Server

Name: QMT-MCP-Server
Author: nnquant

@nnquant

Repository

About QMT-MCP-Server

QMT-MCP-Server

#qmt-mcp-server #stock-trading #model-control-protocol

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "qmt-mcp-server": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is QMT-MCP-Server?

QMT-MCP-Server is a server application based on the Model Context Protocol (MCP) that connects to the Xuntou QMT trading system, enabling large language models to execute stock trading operations. It is intended for learning and exchange purposes only and should be used cautiously in live trading environments.

How to use QMT-MCP-Server?

Install the uv package manager, clone the repository, run uv sync to install dependencies, then execute uv run main.py. On first run, the server prompts for the MiniQMT path and funding account, saving configuration to xttrader.yaml. The server exposes an SSE endpoint at http://localhost:8001/sse for MCP clients.

Key features of QMT-MCP-Server

Account asset query
Position information query
Place orders
Cancel orders

Use cases of QMT-MCP-Server

Query current account holdings
Buy a specified number of shares at a given price
Purchase stocks with a percentage of available capital
Combine with other MCP services for end‑to‑end stock selection and trading

FAQ from QMT-MCP-Server

What are the runtime requirements?

Python 3.10 or higher, a valid QMT trading account, and a locally running MiniQMT instance.

How is the configuration stored?

Configuration (MiniQMT path and funding account) is saved automatically in the xttrader.yaml file after the first run.

What format should stock codes use?

All stock codes must include the exchange suffix, e.g., .SH for Shanghai or .SZ for Shenzhen.

Can stock names be used directly in orders?

Stock names may not be correctly converted to codes by some models; using stock codes is recommended for reliability.

Is this server safe for live trading?

No. The project is for learning and communication only. The author assumes no responsibility for any losses incurred from using this software in live environments.

Comments

More Other MCP servers

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K