Connect FRED (Federal Reserve Economic Data) to Codex

This server connects your AI client to FRED, the Federal Reserve Bank of St. Louis' economic data service, which aggregates hundreds of thousands of time series from US federal statistical agencies and international organizations into one consistent API.

Key features:

• search_series: find the right series by keyword, returning each candidate's id, title, units, frequency and seasonal-adjustment status. Picking the correct series is usually the hard part of economic analysis, so this metadata comes back before you fetch any data.
• get_series_observations: fetch the observations for a series id, with a date range, frequency aggregation, and unit transformations computed upstream (change, percent change, percent change from a year ago, compounded annual rate, log). Missing observations are normalized to null instead of FRED's '.' sentinel.
• list_release_dates: look up the publication calendar - when a statistic such as CPI or the employment situation was or will be released.

Because FRED already harmonizes vintages, units and frequencies across source agencies, it is usually a better first stop than each agency's own API when you need a US macro series.

Using the API requires a free API key issued from your FRED account. Set it as FRED_API_KEY in your Arlet environment variables. FRED's terms ask that you attribute the source; every tool response includes the attribution text.