About tsrs-mcp-server
tsrs-mcp-server is an MCP server written in Rust that wraps TuShare stock market data APIs as query tools for MCP clients. It is built with Poem MCP Server and procedural macros, and is aimed at developers who need A-share data through MCP.
Key features
- 01Wraps TuShare stock market data APIs
- 02Provides limit-up, limit-down and hot list tools
- 03Covers Tonghuashun money flow and concept data
- 04Supports Stdio and Streamable HTTP run modes
- 05Built with Rust, Poem MCP Server and procedural macros
Use cases
- 01Query stocks with consecutive limit-up days
- 02Retrieve Tonghuashun hot rankings and concept fund flows
- 03Fetch A-share minute-level trading data for analysis
MCP support
This project is an MCP server that exposes TuShare interfaces as tools for MCP clients to call.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEtsrs-mcp-server
这是一个基于 Model Context Protocol (MCP) 的TuShare数据服务器,提供了一系列股票市场数据查询接口。
项目简介
本项目是一个Rust实现的MCP服务器,封装了TuShare的API接口,提供了多个股票市场数据查询工具。项目使用了以下主要技术:
- Rust
- Model Context Protocol (MCP)
- Poem MCP Server
- TuShare API
- 过程宏 (Procedural Macros)
功能特性
项目提供了以下MCP工具:
| 工具名称 | 功能描述 | 主要参数 | 返回数据 |
|---|---|---|---|
| limit_step | 获取每天连板个数晋级的股票 | trade_date, start_date, end_date, nums | 股票代码、名称、交易日期、连板次数 |
| ths_hot | 获取同花顺App热榜数据 | trade_date | 股票信息、排名、热度、概念等 |
| kpl_list | 获取涨跌停板数据 | tag, start_date, end_date | 涨跌停详细信息、成交数据等 |
| kpl_concept | 获取开盘啦概念题材列表 | trade_date | 题材代码、名称、涨停数量等 |
| kpl_concept_cons | 获取开盘啦概念题材的成分股 | trade_date, ts_code | 题材成分股详细信息 |
| limit_cpt_list | 获取每天涨停股票最多的概念板块 | trade_date, start_date, end_date | 板块代码、名称、连板数据等 |
| moneyflow_ths | 获取同花顺个股资金流向数据 | ts_code, trade_date, start_date, end_date | 资金流向详细数据 |
| moneyflow_cnt_ths | 获取同花顺概念板块每日资金流向 | trade_date, start_date, end_date | 板块资金流向数据 |
| stk_mins | 获取A股分钟数据 | ts_code, freq, start_date, end_date | 分钟级别的交易数据 |
项目结构
项目包含以下主要组件:
ts-derive: 提供用于TuShare API的过程宏实现ts-model: 包含数据模型src: 主程序实现
环境配置
在运行之前,需要设置TuShare的API token:
- 复制
.env.example为.env - 在
.env文件中设置你的TuShare token:
TUSHARE_TOKEN=your_token_here
构建
前提条件:安装 Rust 和 Cargo。
cargo build --release
./target/release/tsrs-mcp-server
运行
你可以在release中找到对应平台下的编译产物, 例如 tsrs-mcp-server-<tag>-aarch64-apple-darwin.tar.gz。
服务器支持两种运行模式:
- Stdio模式(默认):直接下载release产物。执行:
./tsrs-mcp-server stdio - Stream模式:提供Streamable HTTP模式。endpoint: http://127.0.0.1:8999
运行方式如下图配置(仅展示在chatwise的配置):

鸣谢
感谢以下项目和库, 尤其是 poem-mcpserver 对MCP编写的极强便捷性支持, 没有它, 本项目没有如此简便的实现方式。
同时感谢 TuShare API 提供的数据接口。
最后要感谢 rust, 没有 procedural macros, 本项目的模版实现将变得异常机械化。
License
本项目采用 MIT 许可证。详见 LICENSE 文件。
Comments
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.