Yahoo Finance MCP Server
Enables AI assistants to access Yahoo Finance data including stock information, news, price history, options, and earnings via MCP tools.
README
Yahoo Finance MCP Server
๐ A Model Context Protocol (MCP) server that lets your AI interact with Yahoo Finance - get comprehensive stock market data, news, financials, and more.
โจ Features
- ๐ Stock Data - Get comprehensive ticker information including company details, financials, and trading metrics
- ๐ฐ News Feed - Fetch recent news articles related to specific stock symbols
- ๐ Search - Find stocks, ETFs, and other financial instruments with news results
- ๐ Top Entities - Get top performing companies, ETFs, and mutual funds by sector
- ๐ Price History - Fetch historical price data with customizable periods and intervals
- โก Options Chain - Get option chain data for stocks including calls and puts
- ๐ฐ Earnings - Access earnings data including upcoming earnings dates
- ๐ Proxy Support - Works with HTTP/HTTPS/SOCKS proxies
- ๐ Fast & Async - Non-blocking operations using asyncio
- ๐ง Easy Integration - Standard MCP protocol for AI assistants
๐ Quick Start
Prerequisites
- Python 3.11 or higher
- pip or uvx package manager
- (Optional) Proxy server for better reliability
Installation
Using uvx (Recommended)
# Install with namespace
uvx yahoo-finance-server
Using pip
pip install yahoo-finance-server
From source
git clone https://github.com/AgentX-ai/AgentX-mcp-servers.git
cd AgentX-mcp-servers/yahoo_finance_server
pip install -e .
Configuration
Proxy Setup (Recommended)
For better reliability and to avoid rate limiting, set up a proxy:
# HTTP/HTTPS proxy
export PROXY_URL="http://proxy.example.com:8080"
# SOCKS proxy with auth
export PROXY_URL="socks5://user:pass@127.0.0.1:1080/"
Running the Server
# Basic run (stdio transport)
yahoo-finance-server
# Run with proxy
PROXY_URL="http://127.0.0.1:7890" yahoo-finance-server
# Run with HTTP transport
yahoo-finance-server --transport http --host localhost --port 3000
# Run with HTTP transport and proxy
PROXY_URL="http://127.0.0.1:7890" yahoo-finance-server --transport http --host 0.0.0.0 --port 8080
Transport Options
Stdio Transport (Default)
- Best for development and AI assistant integration
- Communication via stdin/stdout pipes
- Usage:
yahoo-finance-serveroryahoo-finance-server --transport stdio
HTTP Transport
- StreamableHttp transport (replaces deprecated SSE)
- Allows web-based connections and remote access
- Usage:
yahoo-finance-server --transport http --host localhost --port 3000 - Inspector URL:
http://localhost:3000
๐ ๏ธ API Reference
Available Tools
1. get-ticker-info
Get comprehensive stock information including company details, financials, and trading metrics.
{
"name": "get-ticker-info",
"arguments": {
"symbol": "AAPL"
}
}
2. get-ticker-news
Get recent news articles for a stock symbol.
{
"name": "get-ticker-news",
"arguments": {
"symbol": "AAPL",
"count": 10
}
}
3. search
Search for stocks, ETFs, and other financial instruments with related news.
{
"name": "search",
"arguments": {
"query": "Apple Inc",
"count": 10
}
}
4. get-top-entities
Get top performing entities in a sector.
{
"name": "get-top-entities",
"arguments": {
"entity_type": "companies", // Options: "etfs", "mutual_funds", "companies", "growth_companies", "performing_companies"
"sector": "technology", // See supported sectors below
"count": 10
}
}
Supported sectors:
- basic-materials
- communication-services
- consumer-cyclical
- consumer-defensive
- energy
- financial-services
- healthcare
- industrials
- real-estate
- technology
- utilities
5. get-price-history
Get historical price data with customizable periods and intervals.
{
"name": "get-price-history",
"arguments": {
"symbol": "AAPL",
"period": "1y", // Options: 1d, 5d, 1mo, 3mo, 6mo, 1y, 2y, 5y, 10y, ytd, max
"interval": "1d" // Options: 1m, 2m, 5m, 15m, 30m, 60m, 90m, 1h, 1d, 5d, 1wk, 1mo, 3mo
}
}
6. ticker-option-chain
Get option chain data for stocks.
{
"name": "ticker-option-chain",
"arguments": {
"symbol": "AAPL",
"option_type": "call", // Options: "call", "put", "both"
"date": "2024-01-19" // Optional: YYYY-MM-DD format
}
}
7. ticker-earning
Get earnings data including historical and upcoming earnings.
{
"name": "ticker-earning",
"arguments": {
"symbol": "AAPL",
"period": "annual", // Options: "annual", "quarterly"
"date": "2023-12-31" // Optional: YYYY-MM-DD format
}
}
๐งช Testing
Using MCP Inspector
With Stdio Transport (Default)
npx @modelcontextprotocol/inspector yahoo-finance-server
With HTTP Transport
# Terminal 1: Start server with HTTP transport
yahoo-finance-server --transport http --host localhost --port 3000
# Terminal 2: Connect inspector to HTTP server
npx @modelcontextprotocol/inspector http://localhost:3000
Manual Testing
python -c "
import asyncio
from yahoo_finance_server.helper import get_ticker_info
async def test():
info = await get_ticker_info('AAPL')
print(f'โ
Stock: {info[\"longName\"]}')
asyncio.run(test())
"
๐ Requirements
- Python 3.11+
- yfinance==0.2.62
- requests>=2.31.0
- pandas>=2.0.0
- mcp>=1.9.3
๐ค Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Submit a pull request
๐ License
MIT License - see LICENSE file for details.
๐ Links
- Homepage: GitHub Repository
- Issues: Report Issues
- MCP Documentation: Model Context Protocol
Made with โค๏ธ for the finance community
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.