Federal Reserve Mcp Server
Plugs Claude directly into the Federal Reserve's FRED API to search, fetch, and analyze 800,000 economic time series. Five FRED tools let you search series by keyword, pull metadata, retrieve observations with date filtering and unit transformations, browse the category tree, and inspect data releases. Three DataCanvas tools handle spillover when you fetch multi-series or large datasets, letting you run SQL queries against the results. Built for economic analysis workflows where you need programmatic access to GDP figures, unemployment rates, inflation metrics, or any other Fed dataset without leaving your conversation. Supports parallel multi-series requests and gracefully handles FRED's rate limits with retry backoff.
- GitHub stars
- 1
- tools
- 8
- auth
- Required
- transport
- STDIO, HTTP
- env vars
- 11
- last updated
- Nov 11, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
fedreserve_search_seriesFull-text search across FRED series titles, tags, and notes
Full-text search across FRED series titles, tags, and notes
No parameter schema in public metadata yet.
fedreserve_get_seriesFetch metadata for one or more series — title, units, frequency, observation range
Fetch metadata for one or more series — title, units, frequency, observation range
No parameter schema in public metadata yet.
fedreserve_get_observationsFetch date+value observations for one or more series, with date-range and unit-transform filtering
Fetch date+value observations for one or more series, with date-range and unit-transform filtering
No parameter schema in public metadata yet.
fedreserve_browse_categoriesNavigate the FRED category tree
Navigate the FRED category tree
No parameter schema in public metadata yet.
fedreserve_get_releaseLook up a FRED release by ID or name search, with its associated series
Look up a FRED release by ID or name search, with its associated series
No parameter schema in public metadata yet.
fedreserve_dataframe_describeList active DataCanvas dataframes with provenance, schema, and row count
List active DataCanvas dataframes with provenance, schema, and row count
No parameter schema in public metadata yet.
fedreserve_dataframe_queryRun a SELECT against registered DataCanvas dataframes via DuckDB SQL
Run a SELECT against registered DataCanvas dataframes via DuckDB SQL
No parameter schema in public metadata yet.
fedreserve_dataframe_dropDrop a DataCanvas dataframe by name (opt-in)
Drop a DataCanvas dataframe by name (opt-in)
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
FRED_API_KEY*FRED API key from stlouisfed.org. Required to make any API calls.
FRED_BASE_URLdefault: https://api.stlouisfed.org/fredOverride the FRED API base URL.
FRED_DATASET_TTL_SECONDSdefault: 86400Lifetime of a registered dataframe from creation, in seconds.
FRED_DATAFRAME_DROP_ENABLEDdefault: falseSet to 'true' to enable fedreserve_dataframe_drop; otherwise it remains registered as disabled.
FRED_CLAMP_LIMITSdefault: trueAccept up to 100 series IDs and return IDs beyond the 10-observation or 50-metadata processing limit in deferred_ids; false restores strict limits.
MCP_LOG_LEVELdefault: infoSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
MCP_TRANSPORT_TYPEdefault: httpSelects the HTTP transport.
MCP_HTTP_HOSTdefault: 127.0.0.1The hostname for the HTTP server.
MCP_HTTP_PORTdefault: 3010The port to run the HTTP server on.
MCP_HTTP_ENDPOINT_PATHdefault: /mcpThe endpoint path for the MCP server.
MCP_AUTH_MODEdefault: noneAuthentication mode to use: 'none', 'jwt', or 'oauth'.
Readme
@cyanheads/federal-reserve-mcp-server
Search and fetch ~800K Federal Reserve economic time-series from the FRED API via MCP. STDIO or Streamable HTTP.
Details
- Repository
- github.com/cyanheads/federal-reserve-mcp-server
- Category
- Search & Web Crawling
- Package
@cyanheads/federal-reserve-mcp-server- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
More from cyanheads
- Shift Mcp Server1
- Anime Mcp Server2
- Survey Mcp Server4
- Mcp Ts Template145
- nist-nvd-mcp-server
- open-meteo-mcp-server
- openfda-mcp-server
- wikipedia-mcp-server
- census-mcp-server
- crossref-mcp-server
- eur-lex-mcp-server
- faostat-mcp-server
- fema-mcp-server
- libofcongress-mcp-server
- openfoodfacts-mcp-server
- orcid-mcp-server
- reference-data-mcp-server
- usaspending-mcp-server
- arxiv-mcp-server
- exchange-rates-mcp-server
- openlibrary-mcp-server
- protein-mcp-server
- Pubmed Mcp Server167
- Clinicaltrialsgov Mcp Server100
Related Search & Web Crawling MCP servers
View all
Gilbert Mcphugof1234/gilbert-mcpGilbert meetings: list, search, and fetch transcripts & summaries via MCP.1stars
ArXiv Scoutshawnnygoh/arxiv-scoutSearch and retrieve academic papers directly from arXiv with advanced query capabilities. Extract full text from PDFs to generate summaries, literature reviews,1stars
Rekaai.reka/mcpUnderstand your videos with Reka AI — search, ask questions, and extract insights.0stars
Rainbowgore Stealthee Mcp Toolsrainbowgore/stealthee-mcp-toolsSpot pre-launch products before they trend. Search the web and tech sites, extract and parse pages…0stars
Apex Flow 3D Scraperapexflowlabsllc/apex-flow-web-scraperScrape, crawl and monitor public pages as Markdown with change tracking and source receipts.0stars