Alex2Yang97/yahoo-finance-mcp

This is a Model Context Protocol (MCP) server that provides comprehensive financial data from Yahoo Finance. It allows you to retrieve detailed information about stocks, including historical prices, company information, financial statements, options data, and market news.

Yahoo Finance MCP Server

A lightweight Model Context Protocol (MCP) server that wraps the public Yahoo Finance API and makes a rich set of financial data available to LLM‑powered agents (e.g., Claude). The server exposes a collection of typed tools that an LLM can call to fetch:

Category Tools (short description)
Stock Information get_historical_stock_prices – OHLCV series; get_stock_info – current price, metrics, company details; get_yahoo_finance_news – latest news; get_stock_actions – dividends & splits
Financial Statements get_financial_statement – income, balance sheet, cash‑flow (annual/quarterly); get_holder_info – major, institutional, mutual‑fund, insider holders
Options Data get_option_expiration_dates – available dates; get_option_chain – calls/puts for a chosen expiry
Analyst Information get_recommendations – analyst ratings, upgrades/downgrades

Why it matters for AI

The server is designed to be called from Claude for Desktop (or any MCP‑compatible model) so that the model can augment its reasoning with up‑to‑date market data, news, and ownership information. This turns a pure language model into a financial research assistant without the model having to scrape the web itself.

Real‑world prompts (from the README)

  • “Show me the historical stock prices for NOW over the last 6 months with daily intervals.” → get_historical_stock_prices
  • “Get the quarterly balance sheet for Intuit.” → get_financial_statement
  • “What are the analyst recommendations for Intuit over the last 3 months?” → get_recommendations
  • “Get the options chain for INTU with expiration date 2026‑01‑30 for calls.” → get_option_chain

These examples illustrate how an LLM can ask natural‑language questions and the MCP server translates them into concrete API calls.

Getting started

  1. Run without installing – the README recommends uvx:
    uvx --from git+https://github.com/Alex2Yang97/yahoo-finance-mcp yahoo-finance-mcp
  2. Local development – clone, uv sync to install the dependencies listed in pyproject.toml (Python ≥ 3.14.6, mcp, yfinance, pandas, pydantic, …) and start the server with uv run server.py.
  3. Hook into Claude – edit claude_desktop_config.json to add a yfinance MCP entry that points to the command above, then restart Claude.

License

MIT – free to use, modify, and redistribute.

All details are taken directly from the repository’s README.

Related

  • Project
    shanggqm/codexU

    codexU is a native macOS menu‑bar (and Windows Tauri) app that reads local OpenAI Codex (and optional Claude Code) data to display quota percentages, token‑usage trends, project/skill rankings, a locally‑computed AI‑leadership score, and an estimated API‑cost (“羊毛进度”). All processing stays on the user’s machine; no usage data is uploaded.

  • Project
    estebanstifli/LocalText2Voice

    A free, open-source desktop app for turning long-form text into audiobooks and podcasts using local or cloud AI text-to-speech engines.

  • Project
    InternLM/InternBootcamp

    InternAgentHarness (InternBootcamp) is an open‑source framework for creating, running, and evaluating multi‑turn, tool‑augmented LLM agents. It lets researchers define synthetic tasks, expose verified external tools, manage multi‑round interactions, compute rewards, and log full trajectories for data generation or RL training.

  • Project
    AThevon/genjutsu

    genjutsu is a Claude‑AI plugin that lets you ask an LLM to add or redesign motion‑heavy UI elements. Two main skills – `/genjutsu:cast` for small, targeted animations and `/genjutsu:paint` for full‑scale redesigns – automatically detect your stack (React/Vue/Svelte, Compose, SwiftUI), propose an interaction thesis, generate the code (GSAP, Framer Motion, Compose, SwiftUI, etc.), and run a quick audit for accessibility and performance. Install via a single ZIP bundle or individual skill ZIPs on Claude AI, Claude Code, or Cowork.