Ashare-MCP
A stock market data service for querying A-share market data from Sina and Tencent Finance.
Ashare-MCP 是一个基于 mpquant/Ashare 的股票行情数据服务,通过 MCP (Model Context Protocol) 提供 A 股市场的行情数据查询功能。
特性
- 支持多种周期的行情数据:分钟线(1m, 5m, 15m, 30m, 60m)、日线(1d)、周线(1w)、月线(1M)
- 支持多种股票代码格式:通达信格式(sh000001)、聚宽格式(000001.XSHG)
- 双核心数据源:新浪财经和腾讯财经,提高数据获取的稳定性
- 异步处理,提高性能
- 简单易用的 API 接口
安装
# 通过 GitHub 安装
pip install git+https://github.com/RusianHu/Ashare-mcp.git
# 如果需要使用代理
pip install git+https://github.com/RusianHu/Ashare-mcp.git --proxy socks5://127.0.0.1:10808
# 通过本地安装(开发模式)
git clone https://github.com/RusianHu/Ashare-mcp.git
cd Ashare-mcp
pip install -e .
使用方法
作为 MCP 服务使用
在 MCP 配置文件中添加服务配置:
{
"mcpServers": {
"ashare-mcp": {
"command": "python",
"args": [
"-m",
"ashare_mcp"
],
"alwaysAllow": [
"get_price"
],
"disabled": false
}
}
}
作为独立服务运行
# 使用标准输入输出模式
ashare-mcp
# 使用 HTTP 模式
fastmcp serve ashare_mcp
MCP 工具函数
获取股票行情数据,支持分钟线、日线、周线、月线。
参数 | 说明 | 类型 | 默认值 |
---|---|---|---|
code | 证券代码,如'sh000001'或'000001.XSHG' | string | - |
end_date | 结束日期,格式为'YYYY-MM-DD' | string | 当前日期 |
count | 获取的K线数量 | integer | 10 |
frequency | K线周期,可选值:'1m', '5m', '15m', '30m', '60m', '1d', '1w', '1M' | string | '1d' |
fields | 返回字段列表 | array | 全部 |
返回值: 包含股票代码、行情数据和处理消息的对象。
示例
# 获取上证指数最近5天的日线数据
result = await get_price_ashare_mcp(code="sh000001", count=5, frequency="1d")
# 获取贵州茅台指定日期的历史数据
result = await get_price_ashare_mcp(code="sh600519", end_date="2023-01-01", count=10, frequency="1d")
# 获取分钟线数据
result = await get_price_ashare_mcp(code="sh600519", count=5, frequency="15m")
依赖
- fastmcp>=0.1.0
- pandas
- requests
贡献
欢迎提交 Issues 和 Pull Requests 来帮助改进这个项目!
许可证
Copyright © 2025 RusianHu
Related Servers
Nile Postgres
Manage and query databases, tenants, users, auth using LLMs
YugabyteDB MCP Server
Allows LLMs to directly interact with a YugabyteDB database.
PostgreSQL MCP Server
Execute queries directly on a PostgreSQL database.
dbt-docs
MCP server for dbt-core (OSS) users as the official dbt MCP only supports dbt Cloud. Supports project metadata, model and column-level lineage and dbt documentation.
CData Bing Ads
A read-only MCP server to query live Bing Ads data using CData's JDBC driver.
MongoDB
Interact with MongoDB databases using natural language. Query collections, inspect schemas, and manage data.
Memory-Plus
a lightweight, local RAG memory store to record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.
MySQL MCP Tools
Provides tools for querying and managing a MySQL database.
AskTable
Interact with AskTable SaaS or local deployments to query data sources using natural language.
ThoughtSpot MCP Server
Securely query and retrieve data from your ThoughtSpot instance.