Skip to main content

MCP协议的A股量化分析工具,为AI Agent提供股票推荐、行情分析、K线图绘制等功能

Project description

MCP-A股量化分析服务

基于MCP协议的A股量化分析工具,为AI Agent提供股票推荐、行情分析、K线图绘制等功能

功能特性

  • 📈 A股精选股票推荐
  • 📊 K线图绘制(支持MA5/MA10等技术指标)
  • 🔍 股票历史数据查询
  • 📉 技术指标计算(MACD, BOLL等)
  • 🧮 量化分析模型

快速开始

环境要求

  • Python 3.12+
  • 安装依赖库:
uv add "mcp[cli]" matplotlib 
uv add "mcp[cli]" pandas
uv add "mcp[cli]" tushare

运行服务

mcp dev server.py

MCP配置

"ashare_quant": {
    "command": "uv",
    "args": [
        "--directory",
        "path/mcp-servers/python/mcp-ashare-quant",
        "run", 
        "server.py"
    ],
    "disabled": false,
    "autoApprove": []
}

API说明

股票推荐

  • recommend_a_shares(): 推荐符合条件的A股股票
    • 参数: limit(数量), min_price(最低价), max_price(最高价)等
    • 返回: 股票列表及推荐理由

K线图绘制

  • plot_kline(): 绘制股票K线图
    • 参数: data(股票数据), indicators(技术指标)
    • 返回: 图表文件路径

数据获取

  • get_stock_data(): 获取股票历史数据
    • 参数: code(股票代码), count(数据条数)
    • 返回: OHLCV数据

技术指标

  • calculate_technical_indicators(): 计算技术指标
    • 参数: data(股票数据), indicators(指标列表)
    • 返回: 包含指标值的数据

使用示例

获取股票推荐

recommendations = recommend_a_shares(limit=15)

绘制K线图

data = get_stock_data(code="sh600519", count=20)
plot_kline(data, indicators=["MA5","MA10"])

注意事项

  • 使用前需配置Tushare API token
  • 图表功能需要matplotlib支持
  • 数据获取有频率限制,请合理使用

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_ashare_quant-0.1.6.tar.gz (12.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_ashare_quant-0.1.6-py3-none-any.whl (27.3 kB view details)

Uploaded Python 3

File details

Details for the file mcp_ashare_quant-0.1.6.tar.gz.

File metadata

  • Download URL: mcp_ashare_quant-0.1.6.tar.gz
  • Upload date:
  • Size: 12.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.16

File hashes

Hashes for mcp_ashare_quant-0.1.6.tar.gz
Algorithm Hash digest
SHA256 f0177396a3726ca8171cd56b2b180b4702c1bbf2af1ee7e877c6a26caa7697e1
MD5 035dd740f325d712602c222df1d73ced
BLAKE2b-256 e4da5783e5ab3dbd4758c66abdcf2bf3ca2f483823f553334092f1d7cbe4151c

See more details on using hashes here.

File details

Details for the file mcp_ashare_quant-0.1.6-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_ashare_quant-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 24f660c915f9e34e5969b2260f5e678280f2488f6ff7a0b787e337c19bb8163b
MD5 5aa1905cdaedb1df5e3b578cafdf4d5f
BLAKE2b-256 9617bb965d8d28846d422efc093594651ce80e402fdea3b8077f611be5a2c48b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page