mcp-stock-research
A lightweight MCP server that provides stock research tools for Japanese and US stocks, including price, dividends, valuation, and screening, powered by yfinance.
README
mcp-stock-research
A lightweight MCP (Model Context Protocol) server that provides stock research tools powered by yfinance. Works with any MCP-compatible client, including GitHub Copilot in VS Code.
Supports Japanese stocks (TSE) and US stocks out of the box.
Tools
| Tool | Description |
|---|---|
get_stock_info |
Get current price, PE/PB ratios, dividend yield, and other fundamentals |
get_dividend_history |
Get dividend payment history with annual totals |
screen_high_dividend |
Screen multiple tickers for high-dividend quality (consecutive increases, revenue trend) |
get_valuation_summary |
Multi-model fair value calculation (DDM/DCF/PER/PBR/NAV) with median composite |
Quick Start
Option 1: VS Code + GitHub Copilot (recommended)
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"stock-research": {
"type": "stdio",
"command": "python",
"args": ["path/to/mcp_stock_server/server.py"]
}
}
}
Then ask Copilot things like:
- "What's Toyota's current stock price?" → calls
get_stock_info("7203") - "Show me VYM's dividend history" → calls
get_dividend_history("VYM") - "Screen these for high dividends: 8306, 9433, 8591" → calls
screen_high_dividend - "NTTの理論株価を教えて" → calls
get_valuation_summary("9432")
Option 2: Install as a package
pip install -e ./mcp_stock_server
Then use the CLI entry point in your MCP config:
{
"servers": {
"stock-research": {
"type": "stdio",
"command": "mcp-stock-research"
}
}
}
Requirements
- Python 3.11+
- Internet connection (yfinance fetches data from Yahoo Finance)
How it works
Stock code resolution
- Japanese stocks: Enter a 4–5 digit code (e.g.,
7203) → automatically appended with.Tfor Tokyo Stock Exchange - US stocks: Enter a ticker symbol as-is (e.g.,
AAPL,VYM)
Example output
get_stock_info("7203")
{
"symbol": "7203.T",
"name": "Toyota Motor Corporation",
"sector": "Consumer Cyclical",
"price": 2845.0,
"currency": "JPY",
"pe_ratio": 8.5,
"pb_ratio": 1.1,
"dividend_yield_pct": 2.81,
"timestamp": "2026-04-23T10:30:00"
}
get_dividend_history("VYM")
{
"symbol": "VYM",
"name": "Vanguard High Dividend Yield ETF",
"price": 120.5,
"dividend_yield_pct": 3.12,
"annual_dividends": {
"2022": 3.25,
"2023": 3.48,
"2024": 3.61,
"2025": 3.72,
"2026": 1.85
},
"total_payments": 18,
"latest_dividend": {
"date": "2026-03-25",
"amount": 0.95
}
}
License
MIT
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.