mcpField
Q
Qlib Mcp

Qlib Mcp

Local
github.com/lsj210001Finance3Updated 36w ago

About Qlib Mcp

Qlib MCP exposes Microsoft Qlib research capabilities to AI agents for market-data queries, factor analysis, and strategy backtesting. It covers A-share and U.S. market data and includes help for Qlib expressions.

Key features

  1. 01Initialize the Qlib data environment
  2. 02Query index constituents and historical data
  3. 03Get A-share and U.S. data download commands
  4. 04Run TopK strategy backtests
  5. 05Analyze factor IC and quantile returns
  6. 06Look up expression syntax

Use cases

  1. 01Query security prices and factor data
  2. 02Evaluate the effectiveness of a quantitative factor
  3. 03Backtest a TopK momentum strategy

MCP support

The MCP server exposes Qlib tools for data queries, factor analysis, strategy backtesting, and expression help to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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。

License: MIT Python MCP Qlib


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_topkTopK 动量策略回测,返回年化收益/夏普/最大回撤
qlib_factor_analysisIC 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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.