Stock Data MCP Server
Provides real-time stock market data through Yahoo Finance without requiring an API key. Get quotes, historical data, company information, financial statements, and ticker search capabilities.
README
Stock Data MCP Server
A Model Context Protocol (MCP) server that provides real-time stock market data through Yahoo Finance without requiring an API key. Get quotes, historical data, company information, financial statements, and more.
Features
- 🔍 Real-time Stock Quotes - Current prices, changes, volume, and market data
- 📊 Historical Data - OHLCV data with customizable periods and intervals
- 🏢 Company Information - Detailed company profiles, sectors, and metrics
- 💰 Financial Statements - Income statements, balance sheets, and cash flow
- 🔎 Ticker Search - Find ticker symbols by company name
- 🆓 No API Key Required - Uses public Yahoo Finance data via yfinance
- 🚀 Railway Ready - Deploy to Railway.app with one click
Available Tools
1. get_stock_quote
Get current stock price and trading data.
Parameters:
symbol(string, required): Stock ticker symbol (e.g., "AAPL", "MSFT")response_format(string, optional): "markdown" or "json" (default: "markdown")
Example:
{
"symbol": "AAPL",
"response_format": "markdown"
}
2. get_stock_info
Get comprehensive company information and metrics.
Parameters:
symbol(string, required): Stock ticker symbolresponse_format(string, optional): "markdown" or "json"
Example:
{
"symbol": "TSLA",
"response_format": "json"
}
3. get_stock_history
Get historical price and volume data.
Parameters:
symbol(string, required): Stock ticker symbolperiod(string, optional): "1d", "5d", "1mo", "3mo", "6mo", "1y", "2y", "5y", "10y", "ytd", "max" (default: "1mo")interval(string, optional): "1m", "5m", "1h", "1d", "1wk", "1mo", etc. (default: "1d")response_format(string, optional): "markdown" or "json"
Example:
{
"symbol": "NVDA",
"period": "6mo",
"interval": "1d",
"response_format": "json"
}
4. get_stock_financials
Get company financial statements.
Parameters:
symbol(string, required): Stock ticker symbolstatement_type(string, optional): "income", "balance", "cashflow" (default: "income")quarterly(boolean, optional): true for quarterly, false for annual (default: false)response_format(string, optional): "markdown" or "json"
Example:
{
"symbol": "GOOGL",
"statement_type": "income",
"quarterly": false,
"response_format": "markdown"
}
5. search_ticker
Search for ticker symbols by company name.
Parameters:
query(string, required): Company name or partial nameresponse_format(string, optional): "markdown" or "json"
Example:
{
"query": "Apple",
"response_format": "json"
}
Local Development
Prerequisites
- Python 3.11 or higher
- pip
Installation
- Clone this repository:
git clone <your-repo-url>
cd stock-mcp-server
- Install dependencies:
pip install -r requirements.txt
- Run the server locally (stdio mode):
python stock_mcp.py --transport stdio
Testing with MCP Inspector
npx @modelcontextprotocol/inspector python stock_mcp.py
This opens a web interface where you can test all the tools interactively.
Railway Deployment
Quick Deploy
- Push to GitHub:
git init
git add .
git commit -m "Initial commit"
git remote add origin <your-github-repo>
git push -u origin main
-
Deploy to Railway:
- Go to railway.app
- Click "New Project" → "Deploy from GitHub repo"
- Select your repository
- Railway will automatically detect the Dockerfile and deploy
-
Get Your Server URL:
- Once deployed, Railway provides a public URL like:
https://your-app.railway.app - Copy this URL for Claude Desktop configuration
- Once deployed, Railway provides a public URL like:
Environment Variables
No environment variables required! This server doesn't need API keys because it uses public Yahoo Finance data.
Railway automatically sets the PORT variable - don't override it.
Claude Desktop Integration
After deploying to Railway, add this to your Claude Desktop config:
Config location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Configuration:
{
"mcpServers": {
"stock-data": {
"url": "https://your-app.railway.app",
"transport": "streamable-http"
}
}
}
Replace your-app.railway.app with your actual Railway URL.
Restart Claude Desktop after saving the configuration.
Docker Usage
Build the Image
docker build -t stock-mcp-server .
Run Locally
docker run -p 8080:8080 -e PORT=8080 stock-mcp-server
Test the Server
# Health check
curl http://localhost:8080
# List available tools
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":1}'
Usage Examples
Get Apple Stock Quote
Request to Claude:
"What's the current price of Apple stock?"
Behind the scenes:
Claude calls get_stock_quote with {"symbol": "AAPL"}
Analyze Tesla Financials
Request to Claude:
"Show me Tesla's latest income statement"
Behind the scenes:
Claude calls get_stock_financials with {"symbol": "TSLA", "statement_type": "income"}
Compare Historical Performance
Request to Claude:
"Compare the 6-month performance of NVIDIA and AMD"
Behind the scenes:
Claude calls get_stock_history multiple times and analyzes the data
Troubleshooting
"Unable to fetch data for symbol"
- Verify the ticker symbol is correct
- Use
search_tickerto find the right symbol - Some international stocks may not be available
Railway Deployment Issues
- Check Railway logs in the dashboard
- Verify the Dockerfile builds successfully locally
- Ensure you're not setting the PORT environment variable manually
Claude Desktop Connection Issues
- Verify the URL has no trailing slash
- Confirm
transportis set to"streamable-http" - Check Claude Desktop logs (Help → View Logs)
- Restart Claude Desktop after config changes
Data Source
This server uses yfinance, an open-source library that retrieves data from Yahoo Finance. The data is provided for informational purposes only and should not be used for trading decisions without verification.
Data Limitations:
- Real-time data may have a 15-20 minute delay
- Some international stocks may have limited data
- Historical data availability varies by symbol
- Financial statements may not be available for all companies
Architecture
Transport: SSE (Server-Sent Events) for Railway, stdio for local development Framework: FastMCP (MCP Python SDK) Data Validation: Pydantic v2 Stock Data: yfinance (Yahoo Finance API wrapper)
License
MIT License - See LICENSE file for details
Contributing
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
Support
For issues or questions:
- Open an issue on GitHub
- Check the MCP documentation
- Review Railway's deployment guides
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.