FRED
Economic data from FRED, the Federal Reserve Bank of St. Louis database: search 800,000 US and international time series (GDP, inflation, unemployment, interest rates, exchange rates), read their values with unit transformations and frequency aggregation, browse categories, releases, release calendars, sources and tags, and see data revisions. Read-only, free API key.
7-day free trial · No credit card · EU-hosted
Ask FRED anything
Try a real prompt against FRED via AnythingMCP — Claude calls the tools, returns the answer. Press Enter on your own message to install on Cloud.
Install FRED on CloudClaude is AI and can make mistakes. Please double-check responses.
Setup in 2 minutes
- 1Start a free trial on cloud.anythingmcp.com.
- 2Click FRED in the connector store. Paste credentials when prompted.
- 3Mint an MCP API key and point your AI client at the generated MCP URL.
Guides for FRED
Step-by-step setup for the most popular AI clients.
Setting up FRED
From the connector definition itself: where to find the credentials, what they need to be allowed to do, and which API this adapter talks to.
FRED (Federal Reserve Economic Data)
This connector reads FRED, the economic database of the Federal Reserve Bank of St. Louis (https://api.stlouisfed.org/fred): about 800,000 US and international time series from more than 100 sources (BEA, BLS, the Federal Reserve Board, the Census Bureau, OECD, IMF, Eurostat and others), with their categories, releases, sources, tags and revision history (ALFRED vintages). Everything is read-only.
Setup (2 minutes, free)
- Sign in or create a free account at https://fredaccount.stlouisfed.org.
- Open API Keys (https://fredaccount.stlouisfed.org/apikeys), request a key and describe the use in one sentence. The key is a 32-character lower-case string and is issued at once.
- Paste it into
FRED_API_KEY. It is sent as theapi_keyquery parameter, together withfile_type=json.
Workflow
- Find a series:
fred_search_serieswith words (search_text), sorted by relevance;order_bypopularity brings the main headline series first. Well known ids: GDP, GDPC1 (real GDP), UNRATE, PAYEMS (payrolls), CPIAUCSL, CPILFESL (core CPI), PCEPI, FEDFUNDS, DFF, DGS2, DGS10, T10Y2Y, MORTGAGE30US, SP500, VIXCLS, DCOILWTICO, DEXUSEU (USD per EUR), M2SL. - Read the values:
fred_get_observations. It returns the latest 1000 observations, newest first; setlimit1 for the latest value,observation_start/observation_endfor a period,unitspc1 for year-over-year percent change,frequencym/q/a withaggregation_methodto aggregate daily data. A value of "." means no observation (e.g. a holiday). - Understand the series:
fred_get_series(units, frequency, seasonal adjustment, notes, last update),fred_get_series_categories,fred_get_series_releaseandfred_get_series_tags. - Browse by topic:
fred_get_categoryandfred_list_category_childrenfrom the root category 0, thenfred_list_category_series. - Releases and calendar:
fred_list_releases,fred_get_release,fred_list_release_series;fred_get_release_datesfor one release andfred_list_release_datesfor all of them (setinclude_release_dates_with_no_datatrue for upcoming dates). - Sources:
fred_list_sources,fred_get_source,fred_list_source_releases. - Tags:
fred_search_tags(e.g. geography or concept tags) andfred_list_tag_seriesto find series having all given tags, e.g.gdp;germany. - Revisions:
fred_list_vintage_dateslists when a series was published or revised;fred_get_observationswithrealtime_start=realtime_end= a vintage date shows the data as known on that day. - What changed:
fred_list_series_updateslists recently updated series.
Reading the data: values are strings in the series units (check units and seasonal adjustment in fred_get_series before comparing). Dates are YYYY-MM-DD and mark the start of the period (2026-04-01 for the second quarter of 2026). Monthly and quarterly series are published with a lag; quote the date of the latest observation, not today. Cite FRED and the original source from the series notes; some series are copyrighted by their source and the notes say so.
Limits and errors: up to 120 requests per minute per key. FRED answers HTTP 400 with an error_message that names the problem: a wrong or missing key ("api_key is not registered"), an unknown series id ("The series does not exist") or an invalid parameter (e.g. a frequency higher than the series' own). 429 means the rate limit was hit: wait a minute.
Out of scope: GeoFRED maps and regional shapes, the bulk FRED v2 release download and series groups are not part of this connector.
Your AI is two clicks away from FRED.
Install the connector, paste your credentials, ask your AI a question. 7-day free trial, no credit card.