Connecting Yahoo Finance with AI

MCP

ChatGPT and Claude started out as apps you log into, ask questions, and get back links or images.

Until recently, there was no simple way for these platforms to “talk” to each other. That’s changing.

Introduced by Anthropic in November, the Model Context Protocol (MCP) lets LLMs connect to tools and data without custom code for each integration. Think of it like a USB-C port for AI.

It acts as a bridge between probabilistic LLMs and traditional code better suited for structured data.

With MCP, you can let AI run actions on your local machine, for example, “Organize the documents on my desktop into folders by topic.”

It has quickly gained adoption with companies including OpenAI, Google, Microsoft, and more supporting it.

Developers are building open source tools to plug into well-known data providers such as Yahoo Finance.

One of those tools is investor-agent.

You can ask broad-based questions like: What are the key financial metrics of Tesla?

And you get something like this in Claude (this should work in the free version, but I did this with the $20 a month Pro plan).

This image is static, but if you click on it, you’ll see an interactive website.

The nice thing about this tool is a) it’s free and b) you don’t need an API key to connect to Yahoo’s data and c) it mitigates hallucinations by using structured data.

Here’s what it can do:

• Stock Analysis: Retrieves ticker reports including company overviews, key metrics, performance indicators, analyst recommendations, and recent upgrades/downgrades.

• Options Data: Provides information on stock options with high open interest, including strike prices, expiration dates, and volatility.

• Price History: Delivers historical price data with customizable time periods, showing daily data for shorter timeframes and monthly aggregated data for longer periods.

• Financial Statements: Accesses income statements, balance sheets, and cash flow statements in both quarterly and annual formats.

• Ownership Information: Retrieves data on institutional holders and mutual fund positions in stocks.

• Earnings & Insider Activity: Presents earnings history with analyst estimates and surprises, plus recent insider trading activity.

• Market Sentiment Analysis: Tracks the CNN Fear & Greed Index, providing current values, historical data, and trend analysis to gauge market sentiment.

• Technical Indicators: Calculates common technical indicators like SMA, EMA, RSI, MACD, and Bollinger Bands to support technical analysis.

Limitations

The tool struggles with more complex queries. For example, I received error messages after asking “Which S&P 500 company had the biggest gain last week?”

You can see why: the tool has to calculate the returns of all 500 stocks. But this looks to be a side project from one engineer. This tool, and others like it, will likely get better.

Side note: I was using it earlier today (Sunday), but Yahoo wasn’t returning any data. That may be due to too many users/ rate limiting by Yahoo. I came across investor-agent on x/twitter.

Getting Started

If you’re not a coder (like me), you might try Cursor or Windsurf—AI coding assistants that walk you through setup in plain language.

These “vibe coding” tools walk you through how to setup. You’re not really coding; you’re prompting the chatbot to fix issues in plain English.

You can copy/ clone the tool at GitHub. Happy hunting!

DIRECTORY

AI Tool Directory

I’ve put together a database of 50+ AI and investing tools categorized by use case, where you can search, for example, by due diligence or AI agents or earnings data. Each company card has a short description and a link to the platform.

I did my best to add all relevant companies, but I know there are probably more out there. If you know of any that should be included, please reach out: [email protected].

I plan to add more data on each company, but I wanted to see what interests readers most first. So please reach out with comments!

To access this (free) database, please recommend AI Street to someone you think will get value from reading AI Street. (Please don’t send this to a burner email; I can see where they go 🙂)

Share the link below and after they join, you’ll receive the database by email.

ICYMI

Check out the last few editions on using AI for investment analysis,* creating customized news feeds and tracking earnings call mentions:

• Vibe Coding SEC Filings

• The Open-Source Project That’s Making SEC API Calls Cheap

• How Quants Are Evolving with LLMs

• Automating Peer Groups

• Analyzing Earnings Call Tone with AI

• Separating Facts from 'AI Nonsense'

• AI Due Diligence: AnalystAI

• Tracking Big Tech's AI Spending

• DeepSeek on Earnings Calls: From Zero to 100+ Mentions

• Demo: AI Agents in Market Analysis

• ChatGPT's Task Scheduling: Automated Market Analysis

• Effective Prompts For Investment Research

*Not investment advice