GeoFRED — Regional Economic Data MCP. Map U.S. economic metrics by state, county, and MSA.
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 GeoFRED — Regional Economic Data provides access to U.S. regional economic data across states, counties, and metro areas. Use this server to pull unemployment rates, median income, and GDP figures from the official GeoFRED database.
It also gives you the GeoJSON boundaries for mapping, letting you compare economic performance geographically.
What your AI agents can do
Get geo shapes
Retrieves GeoJSON boundary files for specified regions (e.g., states, counties) for mapping purposes.
Get regional data
Gets cross-sectional regional economic data, pulling metrics like income or unemployment for defined regions.
Get series group
Inputs a FRED series ID to discover available regional breakdowns, units, and seasonality.
Retrieves GeoJSON-compatible shape files for specified regions (like states or counties) to build mapping visualizations.
Pulls regional economic metrics (e.g., unemployment, income) for multiple geographic areas at a specific point in time.
Takes a standard FRED series ID and reports all available geographic breakdowns, units, and seasonality for that metric.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
GeoFRED — Regional Economic Data: 3 Tools
Use these three tools to define, pull, and map regional economic data across U.S. states, counties, and metro areas.
019d759fget geo shapes
Retrieves GeoJSON boundary files for specified regions (e.g., states, counties) for mapping purposes.
019d759fget regional data
Gets cross-sectional regional economic data, pulling metrics like income or unemployment for defined regions.
019d759fget series group
Inputs a FRED series ID to discover available regional breakdowns, units, and seasonality.
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 GeoFRED — Regional Economic Data, 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
GeoFRED gives you access to U.S. regional economic data across states, counties, and metro areas. You can pull unemployment rates, median income, and GDP figures directly from the official GeoFRED database. You'll also get the GeoJSON boundaries needed for mapping, letting you compare economic performance geographically.
get_regional_data pulls regional economic metrics—like unemployment or income—for multiple geographic areas at a specific point in time. You can pass in a defined region to pull cross-sectional economic data. get_geo_shapes retrieves GeoJSON boundary files for specified regions, such as states or counties, so you can build mapping visualizations. get_series_group takes a standard FRED series ID and reports every available geographic breakdown, unit, and seasonality for that metric.
How GeoFRED — Regional Economic Data MCP Works
- 1 Start by calling
get_series_groupwith a FRED series ID (e.g., UNRATE). This tells you what data is available and which regions can be mapped. - 2 Use the information from the first step to call
get_regional_data, specifying the desired region type (e.g.,county) and the target series ID. This pulls the actual economic metrics. - 3 Finally, call
get_geo_shapesto get the GeoJSON boundaries for the regions you just analyzed, allowing you to visualize the data on a map.
The bottom line is that you link a standard economic indicator (FRED ID) to a geographic area (GeoJSON) using a two-step process: identify the scope, then retrieve the metrics.
Who Is GeoFRED — Regional Economic Data MCP For?
Regional economists and data scientists who need to move past simple national averages. This server is for the analyst who spends hours clicking through disparate dashboards, trying to manually compare median income across counties versus metro areas. It gives you the data structure to build a true geographic economic dashboard.
Uses get_regional_data to compare unemployment rates across different states and MSAs, calculating regional economic disparities.
Uses get_geo_shapes to get county boundaries and then pulls income data via get_regional_data to find high-potential investment zones.
Uses all three tools to model the impact of policy changes by analyzing trends in poverty and income across specific census regions.
What Changes When You Connect
- See regional disparities instantly. Instead of seeing one national unemployment average, you can use
get_regional_datato pull the specific rate for every county or MSA in your dataset. - Visualize data with precision. Use
get_geo_shapesto get GeoJSON boundaries for any region type. This lets you build accurate, color-coded maps (choropleths) of economic activity. - Know what data exists first. Before pulling data, run
get_series_groupon a FRED ID. This confirms if the metric you want (like housing prices) can even be broken down by county or MSA. - Compare diverse metrics easily. The server supports pulling multiple data types—unemployment, median income, poverty—allowing you to build a single, multi-faceted economic dashboard.
- Handle complex geography. You aren't limited to state borders. This tool supports data breakdowns by MSA, BEA, and FRB, giving you granularity most general APIs miss.
Real-World Use Cases
Finding the best place to open a new branch
A corporate strategist needs to find an ideal market. They first use get_series_group to confirm which income metrics are available by county. Then, they use get_regional_data to pull median income for 50 counties. Finally, they use get_geo_shapes to map those 50 counties, visually identifying the highest-growth, lowest-competition zones.
Analyzing historical state economic shifts
A policy researcher wants to track how unemployment changed in a specific state over two decades. They use get_regional_data with the state type and the correct time series ID. They then use get_geo_shapes to ensure the map boundaries are correct for the entire study period, validating the data's spatial scope.
Comparing metro area vs. county poverty rates
An NGO worker needs to compare poverty rates between two different geographic scopes. They run get_series_group to check the available region types. They then run get_regional_data twice: once for the 'msa' type and once for the 'county' type, allowing for direct, apples-to-apples comparison of poverty metrics.
Building a custom dashboard for investors
An investment firm builds a dashboard. They use get_series_group to map out all available economic indicators. They then call get_regional_data repeatedly for various indicator IDs, pulling data across different region types until they have a full picture of the target market's economic health.
The Tradeoffs
Assuming a single endpoint covers everything
Trying to send a single prompt like 'Give me the income and unemployment for the Southeast region' and expecting one answer. This fails because the system needs to know the region type (MSA, county, etc.) and the data types (income, unemployment) separately.
→
First, use get_series_group to validate that both 'income' and 'unemployment' are available for the desired region type. Then, call get_regional_data twice: once for the income series and once for the unemployment series. This structured approach ensures accurate data retrieval.
Ignoring boundary requirements
Running get_regional_data and getting a table of numbers, but having no way to map them visually or understand the physical area they represent. The data is useless for location intelligence.
→
Always follow up data retrieval with get_geo_shapes. This guarantees you get the GeoJSON boundary files necessary to overlay the economic metrics onto an accurate map for visualization.
Forgetting the data pipeline order
Attempting to pull data for a region type (e.g., county) without first confirming that the series ID supports that region type. The call will fail or return incomplete data.
→
The proper order is: 1) Call get_series_group to validate the series ID and region type combination. 2) Call get_regional_data with the validated parameters. 3) Call get_geo_shapes for the visualization.
When It Fits, When It Doesn't
Use this server if your goal requires linking economic data to a precise geographic boundary. You need to compare metrics like GDP or unemployment by county, not just for the whole state. You must use this if you need the GeoJSON files to build a map. Don't use this if you just need a single national time-series chart (use a general time-series API instead). Also, if you only need to know the national average, this server is overkill. You use it when the location is the variable you are analyzing.
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 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually comparing economic data across states is a nightmare.
Today, comparing regions means switching between the Bureau of Economic Analysis website, the Census Bureau, and FRED. You download a spreadsheet for unemployment by state, then a different one for median income by MSA. You spend hours cleaning, merging, and cross-referencing these disparate files just to build a single, coherent dashboard.
With the GeoFRED server, you ask your agent to get the data. It pulls the metrics using `get_regional_data` and, critically, it provides the `get_geo_shapes` to map them. You get the structured data and the boundaries in one workflow. It’s ready for a visualization library.
GeoFRED — Regional Economic Data MCP Server: Map U.S. economic metrics by state, county, and MSA.
The biggest time sink is the validation process. You have to check the FRED site to see if a given series (like poverty) can even be broken down by county, and then check the Census site for the right shape files. This back-and-forth slows down every analysis.
The server handles that validation. You let the agent run `get_series_group` first. It tells you exactly what region types and units are supported for that specific metric, eliminating manual site checks. You just feed the validated IDs into `get_regional_data`.
Common Questions About GeoFRED — Regional Economic Data MCP
How do I get the county boundaries using the get_geo_shapes tool? +
You call get_geo_shapes and specify 'county' as the region type. The output is a GeoJSON file containing the FIPS codes and coordinates for all county boundaries.
What is the best way to compare income across different region types? +
You must run get_series_group first to confirm the series ID supports both the 'msa' and 'county' types. Then, call get_regional_data twice, once for each region type, to pull the comparable metrics.
Do I need to manually join the data from get_regional_data? +
No. The structure of the data returned from get_regional_data is designed to be joined with the shape data from get_geo_shapes using shared regional identifiers (like FIPS codes), making visualization easier.
Can I find out what region types are available for a specific metric? +
Yes, use the get_series_group tool. Give it the FRED series ID, and it returns a list of supported region types, such as 'state' or 'bea'.
How do I use `get_series_group` to check for available region types? +
You enter a FRED series ID (like UNRATE) into get_series_group. The response includes a list of supported region types, letting you know exactly what geographic breakdowns are available for that metric.
What format does `get_geo_shapes` return for mapping? +
The get_geo_shapes tool returns geographic data in GeoJSON format. This makes it immediately compatible with standard mapping tools and visualization libraries.
If I run `get_regional_data`, how do I handle missing data points? +
The get_regional_data tool pulls cross-sectional data directly. It provides null or missing values for regions where data isn't available for the specified time period or metric.
Can I combine `get_series_group` and `get_regional_data` in a single workflow? +
Yes. First, use get_series_group to validate the region type and available series group ID. Then, pass that information to get_regional_data to retrieve the final, structured data.
What is GeoFRED? +
GeoFRED is the geographic extension of FRED. While FRED provides national time series, GeoFRED breaks that data down by state, county, metropolitan area, and Federal Reserve district — enabling regional economic comparisons and choropleth mapping.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
U.S. Census Full — Complete Demographic & Economic Intelligence
The U.S. Census Mega-Server: 14 tools providing comprehensive access to the ACS and County Business Patterns. Analyze population, age, race, income, poverty, education, home values, rent, and businesses across all 50 states, 3,000+ counties, and cities.
Alation
Data catalog orchestration — search assets, audit metadata, and query data via AI.
Metabase (Business Intelligence & Analytics)
Manage your BI environment via Metabase — list dashboards, retrieve visual questions (cards), and search data entities.
You might also like
Plecto
Automate KPI dashboards and data tracking via Plecto — manage registrations, dashboards, and teams directly from any AI agent.
AEGIS Hedging
Energy risk management — manage trades, valuations, and market data via AI.
AlgoDocs
AI document extraction orchestration — parse PDFs, images, and Word docs via AI.