Financial Datasets

Fetches a company's income statement, detailing its revenues, expenses, and net income over a reporting period. Useful for evaluating a company's profitability and operational efficiency. Covers US, UK and French companies: pass market 'UK' or 'FR', or an isin, for a company outside the US.

get_income_statement

Get an ETF or index fund's holdings and each position's weight (percent of net assets) for a fund ticker (e.g. SPY), sourced from SEC fund-holdings filings. Returns the fund's latest filing by default, or the composition as of a past date. Response includes a fund header (as-of period, total net assets, coverage counts) and the holdings sorted by weight descending.

get_index_fund

Retrieves insider ownership statements for a company: what officers, directors, and 10% owners actually HOLD (common shares, options, RSUs), sourced from SEC Form 3 (an insider's initial statement of ownership) and Form 5 (the annual statement). Complements get_insider_trades, which covers the buys and sells in between: trades are the events, ownership statements are the state. Positions are returned as reported per filing, newest first.

get_insider_ownership

Retrieves insider trading transactions for a company, including purchases, sales, and other transactions by company officers, directors, and major shareholders. Useful for tracking insider sentiment and ownership changes.

get_insider_trades

Retrieves SEC 13F institutional holdings sourced directly from EDGAR. Query by filer_cik (what positions a filer holds) OR by ticker (which institutional filers hold this security) — exactly one is required. When no report_period filter is supplied, returns the latest available quarter for the filer or ticker. Ticker-mode rows include filer_cik and filer_name per position; filer-mode rows omit those (the filer is already implied by the query).

get_institutional_holdings

Lists institutional investors (SEC 13F filers) with their CIK and most recent reported name. Optionally filter by case-insensitive name prefix. Use this to discover the filer_cik to pass to get_institutional_holdings.

get_institutional_investors

Retrieves the latest policy interest rates from major central banks (e.g., FED, ECB, BOE, BOJ). Returns a snapshot of each bank's current rate — no parameters required. Prefer get_macro_data with dataset='interest_rates', which also serves rate history.

get_interest_rates

Retrieves forward-looking KPI guidance items issued by company management in earnings releases and SEC filings. Filter by ticker, period (quarterly/annual), metric name, and date range.

get_kpi_guidance

Retrieves historical KPI taxonomy metrics extracted from SEC filings for a company (e.g., subscriber counts, ARPU, units sold). Filter by ticker, period (quarterly/annual), metric name, and date range.

get_kpi_metrics

Retrieves macroeconomic datasets. dataset='yield_curve' returns the daily US Treasury par yield curve: one object per business day with the keys date, 1_month, 1_5_month, 2_month, 3_month, 4_month, 6_month, 1_year, 2_year, 3_year, 5_year, 7_year, 10_year, 20_year, 30_year, values in percent. A tenor is null when it was not published that day (for example the 30-year from 2002 to 2006); null is not zero. Omit both dates to get the latest curve as a single object. Give start_date and/or end_date to get history as an array, newest first (default window: the trailing year). dataset='interest_rates' returns central bank policy rates as a daily series: omit both dates for every bank's newest published rate as an array (one row per bank with the date it is in effect), or give dates plus a bank code (e.g. bank='FED') for that bank's history, one row per calendar day, newest first, 10 rows per page with next_page_url (default window the trailing five years). Each row has bank, name, date, and rate (percent; for the Federal Reserve the midpoint of the target range). The source publishes the daily series weekly, so the newest day is two to nine days behind. dataset='inflation' returns US CPI and the PCE price index: omit both dates for the latest month of all fourteen series (CPI comes out mid-month, PCE about two weeks later, so the two families can show different months), or give dates plus series (e.g. series='cpi_all_sa' or series='pce_core_sa') for that series' history. Each row has date (the reference month, first day), value (index level: 1982-84=100 for CPI, 2017=100 for PCE), change_1m_pct and change_12m_pct (percent, 1 decimal; null when the comparison month was not published, e.g. October 2025 for CPI). The headline inflation rate is change_12m_pct of cpi_all_nsa; the Fed's preferred measure is change_12m_pct of pce_core_sa. dataset='labor' returns the US labor market, i.e. the jobs report (nonfarm payrolls, unemployment rate, participation, hourly earnings), JOLTS job openings, hires, and quits, and weekly jobless claims: omit both dates for the latest print of all 24 series (monthly series on their latest month, weekly jobless claims on their latest week), or give dates plus series (e.g. series='payrolls_sa') for that series' history. Each row has date (the reference period: the first day of the month for monthly series, the week-ending Saturday for weekly), value (in the series' units: thousands of persons, percent, dollars per hour, persons), change_prior and change_year (value minus the prior period and minus the period one year back, same units), and change_year_pct (percent, 1 decimal; null for rates such as unemployment_rate_sa, whose change is in points; null when the comparison period was not published). dataset='gpu_prices' returns the daily GPU rental price index, the market price of an hour of H100, H200, B200, or B300 compute in US dollars per GPU hour: omit both dates for today's price of all four models (refreshed hourly), or give dates plus series (e.g. series='h100') for that model's daily history (from August 2026; default window the trailing 90 days). Each row has date (UTC day), value (USD per GPU hour), stability_band (the spread across providers, same units), change_1d (dollars), change_1d_pct, change_7d_pct, change_30d_pct (percent, 2 decimals; null when the comparison day has no value), and as_of (when today's value was last refreshed). The response carries an attribution for the source (the Computable GPU Index); keep it when showing the data. Useful for the 10-year yield, the 2s10s spread, policy rates, discount rates, real returns, payrolls, the unemployment rate, wage growth, weekly jobless claims, and the cost of AI compute.

get_macro_data

Fetches recent news articles for a specific company or the broad market. Pass a ticker for company-specific news. Call with no arguments for the latest market-moving news, covering AI, macro, rates, earnings, geopolitics, war, energy, crypto, IPOs, housing, and other market-wide topics. Also useful when trying to explain broad price moves — omit the ticker to check for market-wide catalysts.

get_news

Retrieves non-GAAP KPIs reported by a company (e.g., Adjusted EBITDA, Free Cash Flow as defined by the company). Filter by ticker, period (quarterly/annual), metric name, and date range.

get_kpi_non_gaap

Get SEC filings data for a stock ticker or CIK. Returns a list of filings, including the accession number, filing type, report date, and URLs to the filing documents.

get_filings

Retrieves segment breakdowns from all three financial statement types (income statement, balance sheet, cash flow) in a single call. Returns revenue, operating income, and depreciation by product/segment; assets, goodwill, and long-lived assets by segment; and capital expenditure by segment. Essential for sum-of-the-parts valuation and segment-level analysis.

get_segmented_financials

Fetches the most recent price snapshot for a specific stock, including the latest price, trading volume, and other open, high, low, and close price data.

get_stock_price

Provides a list of all available item names that can be extracted from 10-K, 10-Q, and 8-K reports, grouped by filing type.

list_filing_item_types

Retrieves all available filter fields and operators for the stock screener, grouped by category (income statement, balance sheet, cash flow statement, financial metrics, and company attributes like sector and industry). Use this to discover which fields and operators you can use with the screen_stocks tool.

list_stock_screener_filters

Screens and filters stocks by financial metrics, valuation ratios, and company attributes. Combine multiple filter conditions to find stocks matching your investment criteria (e.g., revenue > $1B and P/E ratio < 20). Use list_stock_screener_filters first to see all available fields and operators.

screen_stocks