FRED Series MCP. Calculate and compare official U.S. economic metrics.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
FRED Series — U.S. Economic Time Series provides direct access to the Federal Reserve's database of 816,000+ economic indicators. Use this server to search, retrieve, and transform official data points like GDP, inflation (CPIAUCSL), and unemployment rates (UNRATE).
It handles complex tasks like year-over-year calculations, unit transformations (log, percent change), and historical vintage analysis for financial modeling.
What your AI agents can do
Get observations
Gets actual data values for a FRED time series, supporting date filters, unit transformations, and frequency aggregation.
Get series
Retrieves metadata for a specific FRED series using common IDs like GDP or UNRATE.
Get series updates
Checks which FRED series were recently updated, helping monitor key economic data releases.
Find any economic data series by keyword across 816,000+ indicators using search_series.
Get specific date/value pairs using get_observations, applying transformations like percentage change or logarithmic scaling.
Fetch the full metadata for a specific indicator ID, including its source, unit, and frequency, via get_series.
Monitor which economic series were recently updated, useful for tracking live data releases using get_series_updates.
Determine historical data revisions and vintage dates using get_vintage_dates.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
FRED Series MCP Server: 5 Tools for Economic Data
Use these tools to search, retrieve, and transform official U.S. economic time series data from the Federal Reserve.
019d759fget observations
Gets actual data values for a FRED time series, supporting date filters, unit transformations, and frequency aggregation.
019d759fget series
Retrieves metadata for a specific FRED series using common IDs like GDP or UNRATE.
019d759fget series updates
Checks which FRED series were recently updated, helping monitor key economic data releases.
019d759fget vintage dates
Retrieves historical revision dates for a series, essential for understanding how data has been adjusted over time.
019d759fsearch series
Searches 816,000+ economic time series using keywords, returning matching series details.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with FRED Series — U.S. Economic Time Series, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
FRED Series — U.S. Economic Data gives your AI client direct access to the Federal Reserve's database of over 816,000 economic indicators. You can use this server to search, pull, and transform official U.S. economic data points like GDP, CPI, or unemployment rates. It handles complex financial modeling tasks, including unit transformations and analyzing historical data adjustments. search_series lets you find any economic data series by keyword across the massive database of indicators. get_series fetches the full metadata for a specific indicator ID, giving you its source, unit, and frequency.
To get the actual date/value pairs, use get_observations; this tool supports filtering by date, running transformations like percentage change or logarithmic scaling, and aggregating frequencies. You can monitor which economic series got updated recently by calling get_series_updates, which is key for tracking live data releases. Finally, get_vintage_dates retrieves historical revision dates for a series, letting you see how data was adjusted over time.
How FRED Series MCP Works
- 1 First, use
search_seriesto find the specific indicator ID (e.g., UNRATE) using a keyword or title. - 2 Next, pass that ID and the desired date range to
get_observationsto retrieve the raw data. You can also specify transformations (e.g., percent change) or frequency aggregation (e.g., quarterly). - 3 The system returns a structured dataset containing the requested date, value, and any applied transformations.
The bottom line is you get structured, transformed economic data without leaving your agent's workflow.
Who Is FRED Series MCP For?
Quantitative analysts, financial risk managers, and data journalists need this. They work with massive, complex, official datasets and constantly need to compare indicators—like comparing the federal funds rate to the 10-year treasury yield. This server lets them access and transform that data without manually building complex data pipelines.
Compares multiple series (e.g., CPIAUCSL vs. UNRATE) over long periods, applying unit transformations (log, percent change) to calculate meaningful metrics.
Tracks data revisions and monitors for new economic releases, using get_series_updates and get_vintage_dates to build reports on data integrity.
Retrieves time-series data for specific assets or indices (like SP500) and aggregates it to match the reporting frequency needed for a client presentation.
What Changes When You Connect
- Calculate complex trends: Use
get_observationsto run built-in unit transformations—like calculating the percent change or log of a series—instead of writing the math yourself. - Handle diverse data volumes: The server manages frequency aggregation, letting you pull daily data and instantly view it as quarterly or annual data points, saving manual cleanup.
- Track data revisions: Use
get_vintage_datesto understand if a figure is based on historical revisions. This is crucial for accurate economic reporting. - Discover indicators fast: Instead of browsing 816,000 entries,
search_serieslets your agent find an indicator by keyword—e.g., 'inflation' or 'housing starts'—in seconds. - Stay current on releases:
get_series_updatesmonitors which series just changed. This is vital for time-sensitive financial analysis and reporting. - Get full context:
get_seriesprovides all the metadata (source, unit, frequency) for a specific series ID, ensuring you know exactly what data you are using.
Real-World Use Cases
Analyzing the Yield Curve
A bond analyst wants to compare the 10-year Treasury yield (DGS10) against the federal funds rate (FEDFUNDS). The agent uses search_series to find both IDs, then uses get_observations to pull the time-series data for both, allowing for an immediate comparison of the spread over time.
Quarterly Growth Reporting
An economist needs to report U.S. GDP growth rates for the last five years. The agent uses get_observations with the GDP ID, specifying a unit transformation of 'percent change' and aggregating the frequency to 'quarterly' (q) to generate the required annualized table.
Monitoring Inflation Changes
A financial journalist needs to know the latest CPI data and if it was revised since the last report. The agent first uses get_series_updates to check for recent changes, then uses get_observations on the CPIAUCSL ID to pull the most current, transformed data.
Building a Data Dashboard
A quantitative analyst needs to build a dashboard comparing several indicators. They use search_series to build a list of necessary IDs, then use get_series to gather the metadata for each, finally using get_observations to pull the complete, aggregated time-series dataset.
The Tradeoffs
Treating data like a simple lookup
Trying to find the latest unemployment rate by just querying a single ID without checking if the data is seasonally adjusted or what the frequency is.
→
Always use get_series first to get the full metadata for an indicator ID. This confirms the source, unit, and frequency before you attempt to pull data with get_observations.
Ignoring data history
Assuming the current reported value is the final, authoritative number, especially for complex metrics like GDP.
→
When comparing historical numbers, run get_vintage_dates to see how the series was revised over time. Don't rely on the first number you see.
Over-relying on a single call
Asking the agent to fetch data for ten different indicators in one go, without specifying the exact ID or transformations needed.
→
Start by using search_series to narrow down the 816,000 options by keyword, then gather the specific IDs, and finally execute multiple, targeted calls using get_observations.
When It Fits, When It Doesn't
Use this server if your task requires accessing authoritative, complex, historical U.S. economic time-series data. You need to calculate metrics (like percent change) or aggregate data across different time scales (daily to quarterly).
Don't use this if you simply need a static definition (use get_series for metadata), or if your data is not U.S. economic data (use a specialized industry API instead). If you are trying to build a real-time dashboard that needs data beyond what is in the FRED database, you need a different data source.
Remember: search_series finds the IDs; get_series describes the IDs; get_observations pulls the data.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FRED. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 5 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Pulling economic data today isn't just about knowing the number.
Before, pulling economic data meant jumping between the Federal Reserve website, running manual calculations in Excel, and cross-referencing dozens of data sheets. You'd spend hours just confirming if the 'unemployment rate' was seasonally adjusted, what its true frequency was, and if the number you saw was a preliminary estimate or a final release.
Now, your agent handles that complexity. You ask for the unemployment rate, and the agent uses `get_observations` to retrieve the date/value pairs, automatically applying the correct unit transformations and aggregating the frequency so you get a clean, ready-to-use dataset.
FRED Series MCP Server: Get the data you need, transformed.
You no longer have to manually check if a metric needs a logarithmic transformation or if it should be annualized. The server handles the math and the unit conversions. You just tell it: 'Give me the GDP growth rate, quarter-over-quarter.'
The result is a clean, structured data table—not a collection of raw numbers that require cleanup. The data is ready for analysis, period.
Common Questions About FRED Series MCP
How do I find the correct ID for the U.S. Consumer Price Index? +
Use search_series with keywords like 'Consumer Price Index' or 'CPI'. This searches the 816,000+ indicators and returns the correct ID (CPIAUCSL) and its basic metadata.
Does `get_observations` handle percent change calculations? +
Yes, get_observations supports built-in unit transformations, including percent change. You simply specify the desired unit in the request, and the tool calculates it for you.
What is the difference between `get_series` and `get_observations`? +
Use get_series to get the description, source, and rules of a specific series ID. Use get_observations to get the actual date/value data for that series.
Can I see how old data was revised? +
Run get_vintage_dates with the series ID. This tool accesses historical revision dates, letting you know if the data point has been updated since its initial release.
What if I need data for a different time period? +
When using get_observations, specify your desired start and end dates. The tool filters the data to that exact date range.
How do I use `search_series` to find a series by a general topic like 'inflation'? +
You search by keyword. The search_series tool takes natural language queries like 'inflation CPI' or 'unemployment rate' and returns matching IDs. It's great for finding the right series ID when you don't know the exact code.
Does `get_observations` support unit transformations like log or percent change? +
Yes, it does. get_observations accepts a units parameter. You can specify transformations like 'pch' (percent change) or 'log' directly in the request, so you get the calculated value, not just the raw number.
Is there a way to check which series have been updated recently using `get_series_updates`? +
Yes, get_series_updates tracks recent changes. You can filter the results by macro (large/popular series) or by specific regions. This is key for monitoring time-sensitive economic reports.
How do I get a FRED API key? +
Free and instant! Go to fredaccount.stlouisfed.org/apikeys, create a free account (no credit card), click 'Request API Key', and copy the 32-character key. Takes under 60 seconds.
Multi-server workflows that include FRED Series — U.S. Economic Time Series MCP
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
EBI PDBe
Explore 3D protein structures, ligand interactions, and molecular assemblies from the Protein Data Bank in Europe.
UniProt
Search 250M+ protein sequences with functional annotations, gene names, subcellular locations, and amino acid data from the world's most comprehensive protein knowledge base.
Copernicus Data Space
Access satellite imagery and Earth observation datasets from the EU Copernicus program for environmental and geospatial analysis.
You might also like
Retell AI
Empower your conversational AI to orchestrate, analyze, and automate phone calls or web-based voice agent interactions via Retell.
Bold
Automate payments via Bold Colombia — manage terminals, process transactions, generate payment links, and track settlements from any AI agent.
Prismic
Query and manage your Prismic headless CMS content — search documents, list custom types, and retrieve specific content directly from any AI agent.