tushare-mcp-server
Provides AI assistants with access to Chinese financial market data via the Tushare Pro API, covering stocks, indices, funds, futures, options, bonds, forex, and macroeconomic indicators.
README
tushare-mcp-server
中文文档 | English
A Model Context Protocol (MCP) server for Tushare Pro financial data API. Provides AI assistants (GitHub Copilot, Claude, etc.) with direct access to comprehensive Chinese financial market data — covering A-shares, indices, funds, futures, options, bonds, forex, HK/US stocks, and macroeconomic indicators.
Features
- Universal Query —
tushare_querycalls any of the 173 Tushare Pro APIs - 15 Convenience Tools — Pre-built tools for stocks, indices, financials, funds, and more
- Built-in Documentation —
get_api_doc/search_api_docsfor API parameter lookup - Categorized Index — 173 APIs organized into 18 categories
Data Coverage
| Category | # | Examples |
|---|---|---|
| A-Shares | 37 | stock_basic, daily, weekly, monthly, daily_basic, adj_factor, pro_bar |
| Financials | 9 | income, balancesheet, cashflow, fina_indicator, forecast |
| Market Reference | 23 | margin, top_list, block_trade, hsgt_top10, pledge_stat |
| Indices | 13 | index_basic, index_daily, index_weight, sw_daily, ci_daily |
| Money Flow | 8 | moneyflow, moneyflow_hsgt, moneyflow_ind_ths |
| Funds | 14 | fund_basic, fund_nav, fund_daily, etf_basic, fund_portfolio |
| Futures | 8 | fut_basic, fut_daily, fut_holding, fut_mapping |
| Options | 3 | opt_basic, opt_daily, opt_mins |
| Bonds / CB | 9 | cb_basic, cb_daily, cb_issue, repo_daily, yc_cb |
| HK Stocks | 9 | hk_basic, hk_daily, hk_income, hk_balancesheet |
| US Stocks | 8 | us_basic, us_daily, us_income, us_balancesheet |
| Macro Economy | 14 | shibor, cn_gdp, cn_cpi, cn_ppi, cn_pmi, libor |
| Sector / Concept | 5 | ths_index, ths_daily, dc_index, dc_member |
| Others | 13 | fx_daily, sge_daily, news, trade_cal, etc. |
Prerequisites
- Python 3.10+
- A Tushare Pro account and API token
Quick Start
Install via npx (recommended)
No installation needed — just configure your MCP client:
{
"servers": {
"tushare": {
"type": "stdio",
"command": "npx",
"args": ["-y", "tushare-mcp-server"],
"env": { "TUSHARE_TOKEN": "your_token_here" }
}
}
}
Install from source
git clone https://github.com/erwanjun/tushare-mcp-server.git
cd tushare-mcp-server
python3 -m venv .venv
source .venv/bin/activate
pip install mcp httpx
Configuration
Tushare Token
Set your token via any of these methods:
.envfile (recommended) — create.envin the project root:TUSHARE_TOKEN=your_token_here- Environment variable —
export TUSHARE_TOKEN=your_token - MCP client config — pass via the
envfield (see examples below)
VS Code (GitHub Copilot)
.vscode/mcp.json:
{
"servers": {
"tushare": {
"type": "stdio",
"command": "npx",
"args": ["-y", "tushare-mcp-server"],
"env": { "TUSHARE_TOKEN": "your_token_here" }
}
}
}
Claude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"tushare": {
"command": "npx",
"args": ["-y", "tushare-mcp-server"],
"env": { "TUSHARE_TOKEN": "your_token_here" }
}
}
}
Tools
| Tool | Description |
|---|---|
tushare_query |
Universal query — call any Tushare Pro API |
get_stock_list |
A-share stock list |
get_trade_calendar |
Trading calendar |
get_daily_bars |
Daily OHLCV (unadjusted) |
get_daily_basic |
Daily indicators: PE, PB, market cap, turnover |
get_income |
Income statement |
get_balancesheet |
Balance sheet |
get_cashflow |
Cash flow statement |
get_fina_indicator |
Financial indicators (ROE, ROA, margins) |
get_index_daily |
Index daily bars |
get_moneyflow |
Stock money flow |
get_concept |
Concept / sector classification |
get_concept_detail |
Concept constituents |
get_fund_basic |
Fund list |
get_fund_nav |
Fund NAV |
get_shibor |
Shibor interest rates |
get_api_doc |
Full API documentation by endpoint name |
search_api_docs |
Search API docs by keyword |
Development
# Re-crawl Tushare documentation
python crawl_docs.py
# Rebuild API index
python build_index.py
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.