mcpField
U
US Stock Data MCP Server

US Stock Data MCP Server

Local
github.com/mingyawFinance0Updated 83w ago
Repository

About US Stock Data MCP Server

US Stock Data MCP Server provides local access to historical US stock prices and can refresh them from Yahoo Finance. It is intended for MCP clients that need CSV-backed market data.

Key features

  1. 01Retrieve local historical stock data
  2. 02Update data from Yahoo Finance
  3. 03Store records in local CSV files
  4. 04Configure update start date
  5. 05Write updates atomically

Use cases

  1. 01Look up historical prices for a stock symbol
  2. 02Refresh locally stored price history
  3. 03Provide stock history to an MCP client

MCP support

Exposes `get_local_stock_data` and `update_stock_data` tools, plus the `usstock://{symbol}/historical` resource, to MCP clients.

#us-stock-mcp-server#stock-data#data-access

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

US Stock Data MCP Server

A Model Context Protocol (MCP) server designed for accessing and updating US stock historical price data.

Features

  • Local Data Storage: Store stock data in CSV format locally for quick access
  • Automatic Updates: Support for automatic stock data updates from Yahoo Finance
  • Safe Data Writing: Use temporary files to ensure atomic and secure data writing
  • Flexible Time Range: Customizable start date for data updates

Installation

  1. Ensure Python 3.x is installed
  2. Clone this repository
  3. Install dependencies:
pip install -r requirements.txt

Usage

1. Start the Server
python server.py

The default data storage path after server startup is: ~/Library/Application Support/us-market-data/data

You can customize the data storage path using the US_STOCK_DATA_DIR environment variable.

2. Available Features
MCP Tools

  1. get_local_stock_data

    • Function: Retrieve local stock historical data
    • Parameters:
      • symbol: Stock symbol, e.g., 'AAPL', 'MSFT'

  2. update_stock_data

    • Function: Update stock data
    • Parameters:
      • symbol: Stock symbol, e.g., 'AAPL', 'MSFT'
      • start_date: Start date in YYYY-MM-DD format, defaults to 2015-01-01
MCP Resources
  • Resource URI: usstock://{symbol}/historical
    • Function: Provide local US stock historical price data
    • Parameters:
      • symbol: Stock symbol

Data Format

The stored stock data includes the following fields:

  • Date: Trading date
  • Open: Opening price
  • High: Highest price
  • Low: Lowest price
  • Close: Closing price
  • Volume: Trading volume

Dependencies

  • mcp: MCP protocol implementation
  • pandas: Data processing and analysis
  • yfinance: Yahoo Finance data retrieval
  • pydantic: Data validation and settings management

Notes

  1. Duplicate data is automatically handled during updates, keeping the latest records
  2. A 5-second delay is implemented between update operations to avoid frequent API requests
  3. All data operations include error handling to ensure service stability

Comments

Markdown supported

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.