findata-mcp-server
FinData enables your AI agents retrieve financial data from different providers like Tushare, Wind, and DataYes.
Documentation
Overview
FinData is an open-source Model Context Protocol(MCP) Server that provides professional financial data access capabilities for LLM. It supports various data providers such as Tushare, Wind, DataYes, etc. This enables AI applications to quickly retrieve financial data.
Fully supports both Stdio and SSE transports, offering flexibility for different environments.
Demonstration
https://github.com/user-attachments/assets/1a6d02af-22a3-44a0-ada7-a771a1c4818d
Quick Start
Prerequisites
Before getting started, please complete the following preparations:
- python => 3.11
- mcp[cli]>=1.6.0
- pandas>=2.2.3
- uv
Depending on your data provider, install optional packages such as:
- tushare>=1.4.21
Configuration
Stdio Transport
You will need to edit the MCP client configuration file to add finData:
{
"mcpServers": {
"finData": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/finData-mcp-server/src/findata",
"run",
"server.py"
],
"env": {
"DATA_API_TOKEN": "", // API Token for accessing data provider
"PROVIDER": "tushare" // Specified data provider
}
}
}
}SSE Transport
Set the environment variables `DATA_API_TOKEN` and `PROVIDER` on the server hosting the MCP Server:
Windows
set DATA_API_TOKEN=
set PROVIDER=Linux
export DATA_API_TOKEN=
export PROVIDER=Then, start the MCP Server:
uv run server.py --transport sse- Optional Arguments:
`--sse-host` Host to bind SSE server to (default: localhost)
`--sse-port` Port for SSE server (default: 8000)
Once the MCP Server is running, update your MCP client's configuration with the following settings to connect to it.
{
"mcpServers": {
"finData": {
"name": "finData",
"type": "sse",
"baseUrl": "http://localhost:8000/sse"
}
}
}Note: Variable names in configuration files may vary slightly between MCP clients. Refer to each client's documentation for proper configuration.
Supported Data Providers
Set the `PROVIDER` environment variable to specify your provider:
- tushare
Tools
Tushare
Market Data
- `daily` Get unadjusted daily stock market data.
Fundamental Data
- `stock_basic` Get stock basic information including name, code, etc.
- `stock_company` Get listed company basic information.
- `bak_basic` Get fundamental data for specific stocks within a given time range.
Financial Data
- `income` Get company income statement data.
- `balancesheet` Get company balance sheet data.
- `cashflow` Get company cash flow statement data.
Macroeconomic Data
- `shibor_lpr` Get Loan Prime Rate (LPR) data.
- `cn_gdp` Get Gross Domestic Product (GDP) data.
- `cn_cpi` Get Consumer Price Index (CPI) data.
- `cn_ppi` Get Producer Price Index (PPI) data.
- `cn_m` Get Money Supply data.
- `sf_month` Get Social Financing data.
- `cn_pmi` Get Purchasing Managers' Index (PMI) data.
DataCanvas

This project is open-sourced by DataCanvas
Frequently asked questions
What is findata-mcp-server?
findata-mcp-server is FinData enables your AI agents retrieve financial data from different providers like Tushare, Wind, and DataYes.
How do I install findata-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is findata-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/zlinzzzz/finData-mcp-server and has 45 stars.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP