Qlib MCP Server

Microsoft Qlib quantitative research platform MCP server for AI agents

README.md

qlib-mcp

全网首个 Microsoft Qlib 量化研究平台的 MCP Server — 让 AI Agent 直接调用 Qlib 做数据查询、因子分析和策略回测。


功能概览

工具 说明
qlib_init 初始化 Qlib 数据环境(必须首先调用)
qlib_download_data 获取 A 股/美股数据集下载命令
qlib_list_instruments 查询 CSI300/CSI500 等指数成分股列表
qlib_get_data 查询历史价格与因子数据(支持 Qlib 表达式)
qlib_backtest_topk TopK 动量策略回测,返回年化收益/夏普/最大回撤
qlib_factor_analysis IC 分析 + 分位数收益,快速验证因子有效性
qlib_expression_help 表达式语法帮助(算子列��� / Alpha158 说明)

安装

前置依赖

# Python 3.10+(推荐 3.12)
pip install pyqlib mcp

下载 Qlib 数据(A 股日线,约 500MB)

python -m qlib.run.get_data qlib_data \
  --target_dir ~/.qlib/qlib_data/cn_data \
  --region cn

注册到 MCP 客户端

Claude Desktop / mcporter / Cursor:

{
  "mcpServers": {
    "qlib": {
      "command": "python",
      "args": ["/path/to/qlib-mcp/server.py"],
      "description": "Microsoft Qlib 量化研究平台"
    }
  }
}

请将 python 替换为你实际的 Python 路径(如 /Users/你/.pyenv/versions/3.12.12/bin/python


使用示例

1. 初始化

调用 qlib_init,data_path = "~/.qlib/qlib_data/cn_data",region = "cn"

2. 查询 CSI300 成分股

调用 qlib_list_instruments,market = "csi300",start_date = "2024-01-01"

3. 获取平安银行近 60 日收盘价

调用 qlib_get_data,symbols = "SZ000001",fields = "$close,$volume",start_date = "2024-10-01"

4. 20 日动量因子 IC 分析

调用 qlib_factor_analysis,factor_expr = "$close / Ref($close, 20) - 1"

5. TopK 策略回测(CSI300,2020-2023)

调用 qlib_backtest_topk,market = "csi300",topk = 50,signal_field = "$close / Ref($close, 20) - 1"

Qlib 表达式语法速查

# 价格动量
$close / Ref($close, 20) - 1      # 20 日动量

# 技术指标
EMA($close, 12) - EMA($close, 26) # MACD
($close - Mean($close, 20)) / Std($close, 20)  # 布林带位置

# 成交量因子
$volume / Mean($volume, 20)        # 相对成交量
Corr($close, $volume, 10)          # 价量相关性(聪明钱)

完整算子列表:调用 qlib_expression_help(topic="operators")


受支持的市场

区域 常用成分股池
A 股(cn) all, csi300, csi500, csi100, sz50
美股(us) sp500, nasdaq100

许可证

MIT License


相关链接

Tools 7

qlib_initInitializes the Qlib data environment.
qlib_download_dataProvides commands to download A-share or US stock datasets.
qlib_list_instrumentsQueries index constituent lists such as CSI300 or CSI500.
qlib_get_dataQueries historical price and factor data using Qlib expressions.
qlib_backtest_topkPerforms TopK momentum strategy backtesting and returns performance metrics.
qlib_factor_analysisPerforms IC analysis and quantile returns to validate factor effectiveness.
qlib_expression_helpProvides help with expression syntax, operator lists, and Alpha158 explanations.

Try it

Initialize the Qlib environment using the data path ~/.qlib/qlib_data/cn_data for the cn region.
List the CSI300 constituent stocks starting from 2024-01-01.
Get the closing price and volume for SZ000001 from 2024-10-01.
Perform an IC analysis for the 20-day momentum factor defined as $close / Ref($close, 20) - 1.
Run a TopK 50 backtest on the CSI300 market using the 20-day momentum signal.

Frequently Asked Questions

What are the key features of Qlib MCP?

Direct AI agent integration with Microsoft Qlib. Support for A-share and US stock market data. Built-in factor analysis and IC validation tools. Automated strategy backtesting with performance metrics. Support for complex Qlib expressions and technical indicators.

What can I use Qlib MCP for?

Automating financial data retrieval for quantitative research. Rapidly validating new trading factors using IC analysis. Backtesting momentum-based trading strategies on historical market data. Querying index constituent lists for portfolio construction.

How do I install Qlib MCP?

Install Qlib MCP by running: pip install pyqlib mcp

What MCP clients work with Qlib MCP?

Qlib MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Qlib MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare