Discovery

The Discovery Module contains lists of companies, cryptocurrencies, forex, commodities, ETFs and indices including screeners, quotes, performance metrics and more to find and select tickers to use in the Finance Toolkit.

Every function of the Discovery module has its own page showing how to use it with the MCP and in Python. Pick one from the sidebar on the left.Every function of the Discovery module has its own page showing how to use it with the MCP and in Python. Pick one from the documentation menu.

Use it in Claude, ChatGPT or another AI assistant through the Finance Toolkit MCP, or install the Python package:

pip install financetoolkit -U

Getting Started

Every analysis starts with a list of tickers, and often you don’t have one yet. The Discovery module is where you find it: complete lists of stocks, ETFs, indices, cryptocurrencies, forex pairs and commodities, a search by name, a stock screener, the day’s market movers and the performance and valuation of whole sectors. Whatever it returns can go straight into the Toolkit for further analysis.

Loading the Module

Discovery is a class of its own and needs only an API key. To initialize it:

from financetoolkit import Discovery

API_KEY = "FINANCIAL_MODELING_PREP_KEY"

discovery = Discovery(api_key=API_KEY)

Lists of Instruments

Each asset class has its own list function: get_stock_list, get_etf_list, get_index_list, get_crypto_list, get_forex_list and get_commodity_list. The stock list alone holds more than 90,000 symbols from exchanges around the world, each with its name.

To retrieve every available stock:

discovery.get_stock_list()

Searching for Instruments

A list that long is easier to search than to browse. search_instruments finds every instrument whose ticker or name matches a query, with the currency and exchange it trades on, which matters for companies listed in several places.

To find every instrument matching “Apple”:

discovery.search_instruments("Apple")

Which returns Apple’s listings on several exchanges first, among others:

The results continue with partial matches such as the Appleseed Fund and Apple Hospitality REIT, so check the name before you use a ticker.

Screening Stocks

The stock screener narrows the full universe down with lower and upper bounds on market cap, price, beta, volume and dividend, and filters on sector, industry, country and exchange. Each bound is optional, so a screen can be as broad or as narrow as you need.

To find stocks with a market cap up to $200 billion, a price between $100 and $200, a beta between 1 and 1.5, a daily volume between 100,000 and 2 million shares and a dividend between $1 and $2 per share:

screener = discovery.get_stock_screener(
    market_cap_higher=1000000,
    market_cap_lower=200000000000,
    price_higher=100,
    price_lower=200,
    beta_higher=1,
    beta_lower=1.5,
    volume_higher=100000,
    volume_lower=2000000,
    dividend_higher=1,
    dividend_lower=2,
    is_etf=False,
)

The result holds each company’s name, market cap, sector, industry, beta, price, dividend, volume, exchange, country and currency, plus the market cap converted to US dollars so that companies listed in other currencies compare directly. 23 stocks pass this screen, from Wheaton Precious Metals at about $60 billion down to Alamo Group at $1.8 billion. Counted per sector:

Industrials make up 10 of the 23, followed by five consumer cyclical and four basic materials companies, with a single technology stock among them.

Gainers, Losers and Most Active Stocks

The day’s market movers are a quick way to spot what is drawing attention: the biggest gainers, the biggest losers and the most actively traded stocks, each with the price, the change in dollars and in percent, and the exchange.

To retrieve the first rows of each:

discovery.get_biggest_gainers().head()

discovery.get_biggest_losers().head()

discovery.get_most_active_stocks().head()

The gainers and losers lists are dominated by small companies with large percentage moves, so they are a starting point for a closer look rather than a list to act on.

Sector Performance and Valuation

Before you dive into individual stocks, it helps to know how their sector is doing. Pass a date to get_sector_performance for a snapshot of every sector on that day, or a sector or industry name to get_sector_pe for that sector’s valuation over time. Together they tell you whether a move is sector-wide or specific to one company, and whether a sector trades rich or cheap compared to its own history. get_industry_performance and get_industry_pe do the same per industry.

To get the performance of every sector on 1 February 2024, the P/E ratio of the Technology sector since 2019 and the P/E ratio of every sector on 16 October 2026:

discovery.get_sector_performance(date="2024-02-01")

discovery.get_sector_pe(sector="Technology", start_date="2019-01-01")

discovery.get_sector_pe(date="2026-10-16")

Without a start_date, the history of one sector covers the past year.

The first gives the average change of the stocks in each sector on that day:

Utilities and consumer stocks rose about 2% that day while financial services fell 2.5%, a split that a single index return would hide. The day before, New York Community Bancorp’s surprise loss had revived worries about regional banks.

The second gives the daily P/E ratio of the Technology sector, shown here as a monthly average against its average over the period, and the third the P/E ratio of every sector on one day, one per tab:

Technology’s P/E went from about 27 at the start of 2019 to above 60 in early 2022, then fell below 30 by the end of that year as rising interest rates hit growth stocks. At about 47 it now trades close to its average of 46 since 2019. Across sectors, consumer cyclical (69) and technology (44) are the most expensive and energy (15) the cheapest.

From Discovery to the Toolkit

The screener returns the tickers as its index, which is exactly what the Toolkit takes. That makes a screen the first step of an analysis: find the candidates, then compare their prices, statements, ratios and risk.

To run the same screen and load the resulting tickers into the Toolkit:

from financetoolkit import Toolkit

tickers = discovery.get_stock_screener(
    market_cap_higher=1000000,
    market_cap_lower=200000000000,
    price_higher=100,
    price_lower=200,
    beta_higher=1,
    beta_lower=1.5,
    volume_higher=100000,
    volume_lower=2000000,
    dividend_higher=1,
    dividend_lower=2,
    is_etf=False,
).index.tolist()

companies = Toolkit(tickers=tickers, api_key=API_KEY)

companies.get_historical_data()

Without a start_date the Toolkit retrieves the last five years. The cumulative return of each screened stock over that period against its beta, with the stocks that beat the S&P 500 in orange:

Stocks that look alike on beta, price and dividend still end up far apart: Wheaton Precious Metals gained 281% and Estée Lauder lost 64%, and only eight of the 22 stocks with five years of prices beat the S&P 500’s 81%. Beta doesn’t separate the winners from the losers. From here, every other module, from ratios to risk, works on the same companies instance.

More in the Discovery Module

The module also covers news (stock, crypto and forex news, press releases and search), the IPO calendar with disclosures and prospectuses, the stock split and earnings calendars, delisted companies, recent mergers and acquisitions, 8-K filings and the latest insider trades.