Shibui Finance is a free MCP server that connects ChatGPT to 64 years of US stock market data. It covers nearly 10,000 NYSE and NASDAQ companies with 31M+ daily price records (1962 to present), quarterly and annual financial statements, daily valuations, and 56 pre-calculated technical indicators. You connect it to ChatGPT once as a developer mode app and then ask questions in plain English. ChatGPT queries the database directly and returns structured results. No downloads, no scripts, no API keys.
Using Claude instead? See How to Get Stock Data into Claude - Claude supports MCP natively and the setup is even simpler.
The old way: CSV uploads and web browsing
If you have tried to use stock data in ChatGPT before, you probably followed one of these paths. Download a CSV from Yahoo Finance, clean up the columns, upload it to a custom GPT, and hope the file is not too large. Or use ChatGPT's web browsing to look up individual figures one at a time. Or build a custom GPT with an API wrapper to pull data on demand.
These approaches work for narrow use cases. But they share the same limitations: you are restricted to whatever data you thought to download in advance, each upload is a one-time snapshot that goes stale immediately, web browsing is too slow for cross-market analysis, and API wrappers require coding and API key management. Comparing two companies means two downloads. Screening across nearly 10,000 companies is not possible with any of these methods.
The MCP approach: connect once, ask anything
MCP (Model Context Protocol) is an open standard for connecting AI models to external data sources. ChatGPT supports MCP via developer mode apps. Instead of uploading files, you give ChatGPT a persistent connection to a database. ChatGPT can then query that source directly, on demand, as part of any conversation. Shibui Finance is an MCP server purpose-built for financial data.
"What was Apple's revenue growth rate each quarter for the last 3 years?"
ChatGPT queries the Shibui database directly and returns the results in a structured format. No download step, no browsing, no script. The data is always current (updated daily, end-of-day), and you can follow up with any question about any company without uploading anything new.
What data is available
- Daily prices - OHLCV data from 1962 to present, 31M+ records across nearly 10,000 securities
- Quarterly and annual financial statements - income statement, balance sheet, and cash flow from 1990 to present
- Daily valuations - market cap, P/E, P/B, enterprise value from 1993 to present
- 56 pre-calculated technical indicators - RSI, MACD, SMA, Bollinger Bands, and more, computed daily for every stock
- Quarterly earnings - actual vs. estimate EPS, surprise percentage, and report dates
- 6.4M SEC EDGAR filing metadata - form types, filing dates, 8-K item codes, accession numbers, and EDGAR links (metadata only, no filing text)
- Nearly 10,000 US-listed securities - stocks, ETFs, ADRs, and REITs on NYSE and NASDAQ
See the full data documentation for column-level detail on all 13 connected datasets.
Three things you can do that CSV uploads and web browsing cannot
The difference between file uploads and a database connection becomes obvious when your questions span the full market.
"Show me the 10 largest companies by market cap in the Technology sector with their current P/E ratios"
This query runs across the entire universe of nearly 10,000 companies, combining valuation data with sector classification, in under a second. With CSV uploads, you would need to have downloaded valuation data and sector data for every company in advance. Web browsing would take minutes per company.
"Find companies where operating margin exceeded 20% every quarter for 3 years"
This checks 12 individual quarters per company across thousands of companies. That is tens of thousands of data points evaluated in a single query. No CSV file you could practically upload would contain all the quarterly financials needed.
"What was the average stock price change 30 days after an earnings miss of more than 10%?"
Event studies like this line up earnings data with the daily prices that followed at specific time offsets across thousands of historical events. The query scans millions of price records to compute the answer. This kind of cross-market analysis is impossible with uploaded files or web browsing.
Limitations to know about
Shibui covers US equities only. There is no international market data, no options, no crypto, and no index-level data.
All data is end-of-day. There are no real-time quotes and no intraday prices. If you need live prices during market hours, use TradingView or your broker's platform.
The underlying data comes from tier-3 data providers, not Bloomberg or S&P Capital IQ. Coverage and accuracy are good for most analytical work, but this is not institutional-grade data. Extreme values (returns above 1000%) sometimes reflect data errors or corporate actions rather than real moves.
Query results are capped at 300 rows. For broader screens, you need to aggregate or narrow your filters. For international markets, Koyfin or TIKR are better options.
Works with all ChatGPT plans
MCP developer mode apps work on every ChatGPT plan, including the free tier. Shibui Finance itself is free. You connect once through ChatGPT's settings and the connection persists across conversations. The setup instructions walk you through it in about 2 minutes.
Frequently asked questions
How do I get stock data into ChatGPT without uploading CSV files?
Connect Shibui Finance, a free MCP server, to ChatGPT as a developer mode app. It gives ChatGPT direct access to 64 years of US stock market data - 31M+ daily price records, quarterly financial statements, and 56 technical indicators for nearly 10,000 companies. No CSV uploads, no API keys, no code. Setup takes about 2 minutes.
Can I connect ChatGPT to a live stock database?
Yes. MCP (Model Context Protocol) lets ChatGPT connect to external data sources via developer mode apps. Shibui Finance is a free MCP server that gives ChatGPT read-only access to a database of US stock prices, financials, and technical indicators dating back to 1962. ChatGPT queries the database directly and returns structured results.
Does ChatGPT have built-in stock data or real-time prices?
No. ChatGPT does not have built-in stock data. Its web browsing can look up individual figures, but cannot screen thousands of companies or compute derived metrics. With Shibui Finance connected, ChatGPT gets end-of-day prices updated daily after market close. There are no real-time or intraday quotes. For live prices during market hours, use your broker's platform or TradingView.
Is there a free stock data API for ChatGPT?
Shibui Finance is completely free - no API keys, no subscription, no per-query costs. It works with all ChatGPT plans (including Free). Other data sources like Bloomberg Terminal or Refinitiv cost thousands per year. Shibui covers nearly 10,000 US equities with 64 years of history at no cost.
What stock data does Shibui Finance include?
Nearly 10,000 US-listed securities (NYSE + NASDAQ) with daily OHLCV prices from 1962, quarterly and annual financial statements from 1990, daily valuations (P/E, P/B, market cap, EV) from 1993, 56 pre-calculated technical indicators, quarterly earnings with surprise data, and 6.4M SEC EDGAR filing metadata records. See the data sources page for full column-level detail.
Do I need to build my own server to use stock data in ChatGPT?
No. Shibui Finance is a pre-built, hosted MCP server. The database is already loaded with 64 years of data. You connect to it in ChatGPT settings - no server setup, no API keys, no code, no maintenance. Other approaches require building custom servers with API wrappers and handling rate limits yourself.