- Home
- MCP servers
- Financial Data
Financial Data
- python
3
GitHub Stars
python
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"samarth2001-financial-data-mcp-server": {
"command": "python",
"args": [
"path/to/server.py"
],
"env": {
"PYTHONUNBUFFERED": "1"
}
}
}
}You deploy the Financial Data MCP Server to give AI assistants real-time access to financial market data from Yahoo Finance. It exposes stock data, options, news, dividends, and essential calculations, enabling you to query prices, historical data, and analysis through your MCP client with practical, real-time insights.
How to use
You access the server from an MCP client to fetch current stock prices, historical data, options chains, company news, and dividend history. You can request calculated indicators like moving averages, RSI, and Sharpe ratio, and you can compare multiple stocks across various metrics. You can also pull recent headlines for context around a stock.
Practical usage patterns include: asking for the latest price of a ticker, requesting a specific moving average, comparing several stocks by performance, retrieving options data for a given expiration, or getting the latest company news headlines. Ask questions like: “What’s the current price of AAPL?” “Show me TSLA’s 50-day moving average.” “Compare AAPL, MSFT, and GOOGL performance.” “Get SPY options expiring this Friday.” “What is the latest news for NVDA?” “Show me KO’s dividend history over the last 10 years.”
How to install
Prerequisites: ensure you have Python installed on your system and access to a terminal or command prompt.
Install the MCP client tools and data libraries needed by the server.
Run the installation commands exactly as shown:
pip install "mcp[cli]" yfinance pandas numpy
Configuration
Add the server configuration to your Claude Desktop setup so the MCP client can start and communicate with the server.
{
"mcpServers": {
"financial-data": {
"command": "python",
"args": ["path/to/server.py"],
"env": {
"PYTHONUNBUFFERED": "1"
}
}
}
}
Additional notes
Data is sourced from Yahoo Finance and comes with a typical 15–20 minute delay. The server uses automatic caching and rate limiting to provide stable results and to respect data provider terms. The guidance here focuses on practical usage for real-time-like insights, recognizing the delay inherent to the data source.
Troubleshooting
If you encounter missing modules, install the required packages and MCP client: pip install yfinance pandas numpy "mcp[cli]".
If there’s no data for a symbol, verify the ticker symbol and ensure you have internet connectivity.
If the server has issues starting, confirm the Python path in your client configuration and try restarting the client application.
Notes
This MCP server provides a structured interface for stock data, options, news, dividends, and basic financial calculations. It is intended for informational purposes and relies on Yahoo Finance data with typical delays.
Available tools
get_stock_price
Fetch the current stock price and basic information for a given symbol.
get_historical_data
Retrieve historical price data for a stock, with configurable period and interval.
get_options_chain
Obtain the options chain for a stock, with optional expiration date sorting, limit, and order.
get_company_news
Return recent news headlines for a specified company.
get_dividends
Fetch the dividend history for a stock over a specified period.
calculate_moving_average
Compute a moving average for a stock with configurable window and type (SMA/EMA).
calculate_rsi
Calculate the Relative Strength Index for a stock over a given period.
calculate_sharpe_ratio
Compute the Sharpe Ratio for a stock given a period and risk-free rate.
compare_stocks
Compare multiple stocks across a chosen metric such as performance.
clear_cache
Clear the data cache to force fresh retrieval from the data source.