QuantPlay MCP Server
Provides access to the QuantPlay trading API for managing broker accounts, tracking positions, and analyzing holdings. It enables users to interact with their trading data through MCP-compatible clients like Claude Desktop.
README
QuantPlay MCP Server
An MCP (Model Context Protocol) server for the QuantPlay trading API, providing access to account data, positions, and holdings through AI assistants.
Features
- Account Management: Retrieve all broker accounts
- Position Tracking: Get positions by account nickname
- Holdings Analysis: Access holdings data by account nickname
- MCP Integration: Works with Claude Desktop and other MCP-compatible clients
Installation
Install from PyPI:
pip install quantplay-mcp
Or install from source:
git clone https://github.com/your-username/quantplay-mcp.git
cd quantplay-mcp
pip install -e .
Setup
1. Get Your QuantPlay API Key
- Visit QuantPlay and sign up for an account
- Navigate to your API settings to generate an API key
- Copy your API key for the next step
2. Environment Configuration
Create a .env file in your project directory:
QUANTPLAY_API_KEY=your_api_key_here
3. MCP Client Configuration
For Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"Quantplay": {
"command": "python",
"args": [
"-m",
"quantplay_mcp"
],
"env": {
"QUANTPLAY_API_KEY": "your_api_key_here"
}
}
}
}
Example with conda/miniconda:
{
"mcpServers": {
"Quantplay": {
"command": "/Users/YOUR_USERNAME/miniconda3/bin/python",
"args": [
"/Users/YOUR_USERNAME/miniconda3/lib/python3.12/site-packages/quantplay_mcp/server.py"
],
"env": {
"QUANTPLAY_API_KEY": "your_api_key_here"
}
}
}
}
For Other MCP Clients
Run the server directly:
quantplay-mcp
Or use Python module execution:
python -m quantplay_mcp
Available Tools
The MCP server provides three tools:
get_accounts()
- Description: Get all broker accounts for the user
- Parameters: None
- Returns: List of account dictionaries with account details
get_positions(nickname: str)
- Description: Get positions for a specific account
- Parameters:
nickname: The account nickname to query
- Returns: List of position dictionaries
get_holdings(nickname: str)
- Description: Get holdings for a specific account
- Parameters:
nickname: The account nickname to query
- Returns: List of holdings dictionaries
Usage Examples
Once configured, you can use these tools through your MCP client:
# Get all accounts
"Show me all my trading accounts"
# Get positions for a specific account
"What are my positions in my main account?"
# Get holdings for a specific account
"Show me the holdings in my retirement account"
Development
Requirements
- Python 3.11+
- QuantPlay API key
Local Development
- Clone the repository
- Install dependencies:
pip install -r requirements.txt - Set up your
.envfile with your API key - Run the server:
python -m quantplay_mcp
Version
Current version: 0.1.21
Support
For issues and questions:
- Check the Issues page
- Visit QuantPlay Documentation for API details
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。