FRED Tags & Sources MCP. Find exact economic series by combining tags.
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 Tags & Sources — Data Discovery lets your AI agent find precise economic data series. Instead of guessing, you search using intelligent tags—like 'gdp', 'usa', or 'monthly'—to filter through thousands of data points.
It lists all 107 contributing data sources (BLS, BEA, Census) and lets you combine tags (e.g., 'usa' + 'gdp' + 'quarterly') to narrow down exactly the right time-series data.
What your AI agents can do
Get series by tags
Retrieves specific FRED series by matching them against a combination of required and excluded tags.
List sources
Provides a complete list of all organizations that contribute data to the FRED database.
Search tags
Allows searching or browsing the full taxonomy of FRED tags by text or category (e.g., geographic, topic).
The agent retrieves time-series data by cross-referencing multiple tags (like country, topic, and frequency) to isolate a narrow set of relevant indicators.
The agent gets a list of every official organization that contributes data to the FRED database, helping you scope your data origins.
The agent searches the full taxonomy of FRED tags, allowing you to discover what kinds of data exist (e.g., all 'inflation' tags, or all 'quarterly' tags).
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
FRED Tags & Sources — Data Discovery: 3 Tools
Use these three tools to discover, categorize, and retrieve precise economic time-series data from the FRED catalog.
019d759fget series by tags
Retrieves specific FRED series by matching them against a combination of required and excluded tags.
019d759flist sources
Provides a complete list of all organizations that contribute data to the FRED database.
019d759fsearch tags
Allows searching or browsing the full taxonomy of FRED tags by text or category (e.g., geographic, topic).
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 Tags & Sources — Data Discovery, 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 Tags & Sources — Data Discovery lets your AI client find precise economic data series. Instead of just guessing, you search using intelligent tags—like 'gdp', 'usa', or 'monthly'—to filter through thousands of data points. It lists all 107 contributing data sources (BLS, BEA, Census) and lets you combine tags (e.g., 'usa' + 'gdp' + 'quarterly') to narrow down exactly the right time-series data.
search_tags lets your agent search or browse the full taxonomy of FRED tags by text or category. You can look up what kinds of data exist, like all 'inflation' tags or all 'quarterly' tags.
list_sources gives your agent a full list of every official organization that contributes data to the FRED database. You can scope your data origins by seeing which groups are involved.
get_series_by_tags retrieves specific FRED series by matching them against a combination of required and excluded tags. You can cross-reference multiple tags—like country, topic, and frequency—to isolate a narrow set of relevant indicators. You combine tags to find series that match all specified criteria, making sure you get exactly what you're looking for.
How FRED Tags & Sources MCP Works
- 1 Tell your agent the scope of your search (e.g., 'I need US inflation data').
- 2 The agent uses
search_tagsto confirm the relevant tags (e.g.,usa,inflation,monthly) and then callsget_series_by_tagsto find the data. - 3 The agent returns a list of specific series identifiers and their descriptions, which you can then pass to other systems.
The bottom line is that you don't need to know the series ID; you just need to know what you're looking for.
Who Is FRED Tags & Sources MCP For?
Data scientists and quantitative researchers who spend too much time navigating FRED's web interface. If your job involves building automated data pipelines or validating hypotheses based on economic indicators, this is for you. It replaces manual browsing and keyword guessing with structured, programmatic discovery.
Uses get_series_by_tags to programmatically find all relevant indicators for a model build, ensuring every necessary data point is included.
Employs list_sources and search_tags to map out data dependencies, building automated pipelines that pull from diverse sources like BLS and BEA.
Runs complex queries combining tags (e.g., 'usa' + 'gdp' + 'monthly') to validate research hypotheses and build reports.
What Changes When You Connect
- Find the right series: Instead of running keyword searches that return too much noise, use
get_series_by_tagsto filter data by required tags (e.g.,usa) and specific topics (e.g.,gdp). - Map your data origins: Use
list_sourcesto get a full directory of all 107 contributing organizations. This is critical for data lineage and knowing who provided the numbers. - Target metadata precisely:
search_tagslets you browse the entire FRED taxonomy—whether you need to find allquarterlydata or allinflationtags—before you write a single query. - Build complex filters: You can combine multiple tags in one call. This means your agent doesn't just look for 'GDP'; it looks for 'US GDP' that is 'monthly' and 'not seasonally adjusted'.
- Accelerate research: By handling the metadata lookup, the tool cuts out the manual, error-prone step of cross-referencing source documents and tag lists.
- Handle diverse data types: The tags cover geography (
usa,europe), topic (gdp,inflation), and frequency (monthly,quarterly), giving you massive coverage.
Real-World Use Cases
Need to find all US GDP indicators.
A researcher knows they need US GDP data but doesn't know the exact series ID. They ask their agent: 'Find all US GDP indicators.' The agent uses search_tags to confirm the tags (usa, gdp) and then executes get_series_by_tags, returning a list of 47 matching series. The problem is solved without manual browsing.
Need to track data source changes.
A data engineer is building a pipeline that consumes data from multiple government agencies. They ask the agent to list all possible sources. The agent runs list_sources, giving them a full list of 107 contributing organizations, allowing them to map out all potential points of failure or update.
Need to find all quarterly European inflation data.
A quantitative analyst needs to compare inflation across multiple regions. They ask the agent to find data matching europe + inflation + quarterly. The agent uses get_series_by_tags to pinpoint exactly the required series, excluding US data, in one step.
Validating data scope for a new project.
A student is starting a project on consumer spending. Instead of reading the entire FRED guide, they ask the agent to search for tags like consumer and spending. The agent uses search_tags to show them all related tags, helping them scope the project before writing any code.
The Tradeoffs
Using simple keyword search
Asking the agent to 'Find US GDP' without specifying tags. This often returns a list of series that are related but not exactly what you need, forcing you to manually filter the results in a spreadsheet.
→
Use get_series_by_tags and specify multiple tags: usa + gdp + monthly. This forces the query to only return series matching all criteria.
Ignoring source provenance
Pulling a series without knowing if the data comes from the BEA or the BLS. This introduces risk if the source changes its methodology, leading to incorrect analysis.
→
Run list_sources first. Then, use the source tag in conjunction with get_series_by_tags (e.g., bls + gdp) to limit results to a specific, trusted data provider.
Over-relying on general searches
Using a broad search for 'finance data' via search_tags. This generates thousands of tags, and you still have to figure out which combination is correct for your specific project scope.
→
Running multiple separate searches
Calling search_tags for 'gdp', then calling search_tags for 'usa', and then trying to combine them manually. This is slow and error-prone.
→
Use get_series_by_tags in one go. It handles the logic of combining tags like usa + gdp seamlessly to find the intersection of the data sets.
When It Fits, When It Doesn't
Use this server if your core task is finding specific, pre-defined economic time series data. You need to filter down a massive catalog (107 sources, 200k+ series) using structured metadata like geography, topic, or time frequency.
Don't use this if you just need a general idea of economic trends (use a general chat search) or if your data structure is proprietary (use a custom data connector). If you need to know what tags exist, use search_tags. If you need to know who provided the data, use list_sources. If you know the criteria, use get_series_by_tags.
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
Finding the right economic data shouldn't feel like digging through an archive.
Before this, finding a single series was a mess. You'd spend time clicking through different FRED tabs—checking the topic, then checking the source, then checking the frequency—and constantly copying/pasting IDs into a spreadsheet just to confirm the data point. It was slow, and you always risked missing a key tag.
Now, you just tell your agent the criteria. The agent uses the tags to handle the complex filtering logic. You get back a clean list of specific series IDs that match your exact criteria. It's precise, repeatable, and takes seconds.
FRED Tags & Sources — Data Discovery MCP Server
You no longer have to switch between the FRED website and your analysis tool to build context. The agent handles the discovery layer entirely. It uses `search_tags` to understand your intent and then calls `get_series_by_tags` to deliver the actionable data identifiers.
This process removes the guesswork from data sourcing. You get the definitive list of series IDs, fully validated against the entire catalog, every time.
Common Questions About FRED Tags & Sources MCP
How does the FRED Tags & Sources — Data Discovery MCP Server work with the `get_series_by_tags` tool? +
The get_series_by_tags tool lets you retrieve specific data series by matching them against multiple tags. You provide a list of tags (e.g., usa, gdp, monthly), and the tool returns only the series that meet all those criteria.
Can I use `search_tags` to find out what tags are available? +
Yes. search_tags lets you browse or search the full taxonomy of FRED tags. This is useful if you don't know the specific tag name (like nsa or bea) but know the general topic.
Does `list_sources` tell me which data is available? +
No. list_sources only gives you a list of the 107 organizations that contribute data (like BLS or Census). You still need to use get_series_by_tags to find the actual data series from those sources.
What is the best way to combine tags for the MCP Server? +
The best way is to use get_series_by_tags and list your tags as a combination (e.g., tag_names="usa;gdp"). This tells the tool to find the intersection of all specified criteria.
How does `get_series_by_tags` handle combinations of tags, like combining geographic and topic tags? +
It combines tags logically. You pass multiple tags separated by semicolons (e.g., 'usa;gdp') to find series matching all specified criteria. You can also use exclude_tag_names to narrow down results further.
If I need to find data from a specific source, should I use `list_sources` or `search_tags`? +
You should use search_tags. This tool allows you to browse and search for source labels (like 'bls' or 'bea') and then use those labels in get_series_by_tags to filter the results accurately.
Are there any rate limits or performance concerns when using `get_series_by_tags`? +
Vinkius manages the connection to FRED, but heavy usage is subject to FRED's API rate limits. Keep requests efficient by combining tags and using exclusion filters rather than running many simple searches.
What happens if the tags I provide to `get_series_by_tags` are too broad or don't match any data? +
The tool returns an empty set of results. This confirms that no series currently exist matching your exact combination of tags. You'll need to adjust your search parameters.
What is the difference between tags and categories? +
Categories are a strict hierarchy (one parent, many children). Tags are flat labels — each series can have many tags across dimensions: geography (usa), frequency (monthly), topic (gdp), source (bls). Combine tags for powerful cross-dimensional filtering.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Atlan
Search and discover data assets, business glossaries, classifications, policies, and personas directly via your AI agent.
ClinicalTrials.gov
Search the world's largest registry of clinical research studies — covering diseases, drugs, and experimental therapies across all phases.
RCSB PDB
Explore 220K+ 3D molecular structures — search proteins, DNA, and RNA by name, experimental method, resolution, and bound ligands from the Protein Data Bank.
You might also like
Deskpro
Deliver exceptional helpdesk support with ticket management, self-service portals, and SLA tracking across every channel.
Bcrypt Hash Engine
Hash and verify passwords with the industry-standard bcrypt algorithm. Two tools in one: hash with configurable salt rounds, and verify against stored hashes. Pure JS — zero compilation.
Drata
Automate compliance and security via Drata — monitor controls, track personnel onboarding, audit policies, and verify cloud asset security directly from any AI agent.