Tushare Server
БесплатноНе проверенProvides AI assistants with access to Tushare financial data API for querying Chinese stock market data, financial statements, and macroeconomic indicators.
Описание
Provides AI assistants with access to Tushare financial data API for querying Chinese stock market data, financial statements, and macroeconomic indicators.
README
A Model Context Protocol (MCP) server that provides AI assistants with access to Tushare financial data API. This enables AI models to query Chinese stock market data, financial statements, macroeconomic indicators, and more.
Features
This MCP server exposes 18 financial data tools across multiple categories:
Stock Data
- stock_basic - Stock list with basic information (code, name, industry, listing date)
- stock_company - Company profile and basic information
- daily_quote - Daily price data (OHLCV)
- daily_basic - Daily valuation metrics (PE, PB, PS, market cap)
- trade_cal - Trading calendar
Financial Statements
- income - Income statement data
- balance_sheet - Balance sheet data
- cashflow - Cash flow statement data
- fina_indicator - Financial indicators (ROE, gross margin, net margin)
Market Data
- daily_limit - Daily limit-up/limit-down statistics
- moneyflow_hsgt - Stock Connect (Northbound) capital flow
- top10_holders - Top 10 shareholders
Concept & Index
- concept - Concept stock categories
- concept_detail - Concept stock constituents
- index_basic - Index basic information
- index_daily - Index daily quotes
Futures
- future_basic - Futures contract basic info
- future_daily - Futures daily market data
Installation
From Source
git clone https://github.com/lijinly/tushare-mcp-server.git
cd tushare-mcp-server
pip install -e .
Requirements
- Python >= 3.10
- Tushare API Token (Get one free)
Configuration
1. Get Tushare API Token
Register at Tushare Pro and get your API token from your profile page.
2. Configure Environment Variable
# Linux/macOS
export TUSHARE_TOKEN="your_token_here"
# Windows PowerShell
$env:TUSHARE_TOKEN="your_token_here"
# Windows CMD
set TUSHARE_TOKEN=your_token_here
3. Configure MCP Client
Add to your MCP client configuration (e.g., Claude Desktop, Cline):
{
"mcpServers": {
"tushare": {
"command": "python",
"args": ["-m", "tushare_mcp_server"],
"env": {
"TUSHARE_TOKEN": "your_token_here"
}
}
}
}
Claude Desktop Config Location:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Usage
Manual Start
python -m tushare_mcp_server
With MCP Client
Once configured, the AI assistant can directly call Tushare data tools:
Example queries:
- "Get the daily quote for 000001.SZ"
- "Show me the PE ratio of Kweichow Moutai"
- "What's the stock connect capital flow today?"
- "List all concept stocks for artificial intelligence"
Data Format
All tools return JSON formatted data:
{
"data": [...],
"count": 100,
"columns": ["ts_code", "trade_date", "close", "pe", "pb"]
}
Project Structure
tushare-mcp-server/
├── src/tushare_mcp_server/
│ ├── __init__.py
│ ├── __main__.py
│ └── server.py # Main MCP server implementation
├── pyproject.toml # Project configuration
├── README.md
└── .gitignore
Dependencies
| Package | Version | Purpose |
|---|---|---|
| mcp | >=1.0.0 | MCP protocol implementation |
| tushare | >=1.4.0 | Tushare API client |
| pandas | >=2.0.0 | Data manipulation |
Development
Setup Development Environment
# Create virtual environment
conda create -n tushare-mcp python=3.10 -y
conda activate tushare-mcp
# Install in editable mode
pip install -e .
Testing
python -m tushare_mcp_server
Troubleshooting
"TUSHARE_TOKEN environment variable is not set"
Make sure you've set the TUSHARE_TOKEN environment variable before starting the server.
"Error connecting to Tushare API"
- Check your internet connection
- Verify your Tushare token is valid
- Ensure your Tushare account has sufficient API points
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Tushare - Chinese financial data platform
- Model Context Protocol - Open protocol for AI tool integration
Related Links
Установка Tushare Server
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/lijinly/tushare-mcp-serverFAQ
Tushare Server MCP бесплатный?
Да, Tushare Server MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Tushare Server?
Нет, Tushare Server работает без API-ключей и переменных окружения.
Tushare Server — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить Tushare Server в Claude Desktop, Claude Code или Cursor?
Открой Tushare Server на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Tushare Server with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
