stock-price-mcp-server
Enables real-time stock price queries and historical data retrieval for US, Taiwan, and other global markets via Yahoo Finance.
README
Stock Price MCP Server
A FastMCP-based stock price query server providing real-time stock market data.
Features
Powered by yfinance for real-time stock data:
-
get_stock_price(symbol: str)- Get real-time stock price and related information- Supports US stocks (AAPL, GOOGL, TSLA, MSFT, etc.)
- Supports Taiwan stocks (2330.TW, 2317.TW, etc.)
- Returns price, change, volume, market cap, and more
-
get_stock_history(symbol: str, period: str)- Get historical prices- Period options: 1d, 5d, 1mo, 3mo, 6mo, 1y, 2y, 5y, 10y, ytd, max
- Returns OHLCV (Open, High, Low, Close, Volume) data
-
get_stock_info(symbol: str)- Get detailed stock information- Company name, sector, country
- Employee count, market cap, P/E ratio
- 52-week high/low, and more
-
greet(name: str)- Greeting tool
Quick Deploy to FastMCP Cloud
Step 1: Fork or Clone this Repository
git clone https://github.com/YOUR_USERNAME/stock-price-mcp-server.git
cd stock-price-mcp-server
Step 2: Push to Your GitHub
git remote set-url origin https://github.com/YOUR_USERNAME/stock-price-mcp-server.git
git push -u origin main
Step 3: Deploy to FastMCP Cloud
- Go to FastMCP Cloud
- Sign in with your GitHub account
- Click "Create New Project"
- Fill in project information:
- Name:
stock-price-server(or your preferred name) - GitHub Repository: Select your repository
- Entry Point:
server.py:mcp - Authentication: Choose Public or Organization only
- Name:
- Click "Deploy"
Step 4: Use Your Server
After deployment, your server will be available at:
https://your-project-name.fastmcp.app/mcp
You can connect this server in Claude Desktop, Cursor, or other MCP clients.
Local Development
Requirements
- Python 3.10 or higher
- uv (recommended) or pip
- FastMCP CLI
Install Dependencies
Using uv:
uv pip install -r requirements.txt
Run the Server Locally
Start the FastMCP development server:
fastmcp dev server.py:mcp
The server will be available at http://localhost:8000
Note: Don't use uv run server.py - FastMCP servers must be run through the fastmcp CLI tool.
Verify Server Configuration
Inspect the server without running it:
fastmcp inspect server.py:mcp
Test the Server
After starting the server, you can test it using the test client (in a separate terminal):
uv run main.py
Supported Stock Symbols
US Stocks
- AAPL - Apple Inc.
- GOOGL - Alphabet Inc.
- TSLA - Tesla Inc.
- MSFT - Microsoft Corporation
- NVDA - NVIDIA Corporation
- META - Meta Platforms Inc.
Taiwan Stocks
- 2330.TW - Taiwan Semiconductor
- 2317.TW - Hon Hai Precision
- 2454.TW - MediaTek
- 2412.TW - Chunghwa Telecom
Other Markets
- 9988.HK - Alibaba (Hong Kong)
- 600519.SS - Kweichow Moutai (Shanghai)
Usage Examples
Using in Claude Desktop
- Open Claude Desktop settings
- Add MCP server:
{
"mcpServers": {
"stock-price": {
"url": "https://your-project-name.fastmcp.app/mcp"
}
}
}
- Restart Claude Desktop
- Now you can ask: "What's the stock price of AAPL?" or "Show me TSMC's price trend for the last month"
Using FastMCP Client
import asyncio
from fastmcp import Client
async def query_stock():
client = Client("https://your-project-name.fastmcp.app/mcp")
async with client:
# Query real-time stock price
result = await client.call_tool("get_stock_price", {"symbol": "AAPL"})
print(result.data)
# Query historical prices
history = await client.call_tool("get_stock_history", {
"symbol": "TSLA",
"period": "1mo"
})
print(history.data)
asyncio.run(query_stock())
Technical Details
- Data Source: Yahoo Finance (via yfinance package)
- Update Frequency: Real-time (15-minute delay per Yahoo Finance API limits)
- Supported Markets: Major global stock markets (US, Taiwan, Hong Kong, China, etc.)
- Deployment Platform: FastMCP Cloud
- Auto Deployment: Automatically redeploys on push to main branch
- PR Preview: Each PR gets a unique testing URL
File Structure
stock-price-mcp-server/
├── server.py # FastMCP server implementation
├── requirements.txt # Python dependencies
├── pyproject.toml # Project configuration
├── .gitignore # Git ignore rules
└── README.md # Documentation
License
MIT License
Contributing
Issues and Pull Requests are welcome!
Support
For questions:
- Check FastMCP Official Documentation
- Submit a GitHub Issue
- Visit FastMCP Cloud for help
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.