Hello! 👋 If you've ever tried researching a stock online, you know the drill: most websites give you just 3–5 years of data (in free), scattered across cluttered pages full of ads — and when you finally find the numbers you need, there's no way to actually export them to excel. We built ShinobiData to fix that. Full financial statements for all 10,000+ US-listed companies — P&L, balance sheet, cash flow, ratios, valuations — with 20+ years of price history, presented in one clean, organized view. Every company page exports to a formatted Excel file in one click, including a raw SEC-filings version if you want the untouched source data. There's also a screener with 440+ metrics you can query in plain English ("undervalued midcaps with Piotroski ≥ 7"), 19 quant scores, and analyst targets. And for the AI crowd: connect our MCP server to Claude or ChatGPT, paste your Robinhood positions (or a screenshot of your brokerage app), and ask "did I beat the S&P?" or "am I too concentrated in tech?" — 33 tools, all free. Everything is 100% free — no paywall, no card. What data do you always find yourself hunting for that no site shows properly? That's what we'll build next. We'll be here all day! 🥷

Forum Threads

p/shinobidata

•

3d ago

What data would you give Claude/ChatGPT if you wanted truly deep stock research?

When you ask an AI agent to research a stock today, it goes off and searches the web pulls a P&L number from one site, a balance sheet figure from another, maybe a stale ratio from a third. It works, sort of, for one company, one time. But the data is fragmented, often outdated, and the agent starts from zero on every question.

View all

Shinobidata

20+ years of data with clean presentation and zero clutter

20+ years of data with clean presentation and zero clutter

Forum Threads

What data would you give Claude/ChatGPT if you wanted truly deep stock research?

Forum Threads

What data would you give Claude/ChatGPT if you wanted truly deep stock research?