@cyanheads/federal-reserve-mcp-server

Search and fetch ~800K Federal Reserve economic time-series from the FRED API via MCP. STDIO or Streamable HTTP.

8 Tools

Tools

Five FRED tools plus three DataCanvas tools for querying spilled observation results via SQL:

Tool	Description
`fedreserve_search_series`	Full-text search across FRED series titles, units, frequency, and tags — returns matching series IDs with metadata
`fedreserve_get_series`	Fetch metadata for one or more series (title, units, frequency, seasonal adjustment, observation range)
`fedreserve_get_observations`	Fetch date+value observation data for one or more series with date-range filtering and unit transformations
`fedreserve_browse_categories`	Navigate the FRED category tree; drill into a category to see child categories and a series sample
`fedreserve_get_release`	Look up a FRED release by ID or name search — returns release metadata and its associated series list
`fedreserve_dataframe_describe`	List active DataCanvas dataframes registered by this server (canvas IDs, row counts, schemas)
`fedreserve_dataframe_query`	Run a SELECT query against a registered DataCanvas dataframe
`fedreserve_dataframe_drop`	Drop a DataCanvas dataframe by name (opt-in via `FRED_DATAFRAME_DROP_ENABLED=true`)

`fedreserve_search_series`

Search for FRED series by free-text query across titles, tags, and notes.

Full-text and series-ID search modes
Post-search filtering by frequency, units, or seasonal adjustment status
Tag-name filtering (semicolon-delimited list)
Pagination via limit and offset
To find series for a specific release, use fedreserve_get_release instead

`fedreserve_get_series`

Fetch metadata for one or more FRED series.

Accepts up to 50 series IDs in a single call
Returns title, units, frequency, seasonal adjustment, observation range, popularity, and notes
Fires parallel upstream requests (no FRED batch endpoint exists); partial success reported per ID

`fedreserve_get_observations`

Fetch observation data (date + value pairs) for one or more series.

Accepts up to 10 series IDs; fires one upstream request per series in parallel
Date-range filtering with ISO 8601 dates (observation_start, observation_end)
FRED's native unit transformations: lin, chg, ch1, pch, pc1, pca, cch, cca, log
Frequency downsampling with configurable aggregation method (avg, sum, eop)
Multi-series or >500-row results spill to a DataCanvas table; response includes a dataset.name handle for SQL querying via fedreserve_dataframe_query
Degrades gracefully when DataCanvas is unavailable — returns inline preview with row count

`fedreserve_browse_categories`

Navigate the FRED category hierarchy.

Omit category_id to start at the root (ID 0)
Provide a category_id to see child categories and a series sample for leaf categories
Covers all FRED domains: Money & Banking, National Accounts, Employment, Prices, Housing, Trade, and more

`fedreserve_get_release`

Inspect a FRED data release and its associated series.

Look up by release_id (integer) or release_search (case-insensitive substring match)
Name search fetches all releases and filters client-side (FRED has no server-side release search)
Returns release name, link, scheduled dates, and a paginated series list
Use series_limit and series_offset to page through large releases

Features

Built on @cyanheads/mcp-ts-core:

Declarative tool definitions — single file per tool, framework handles registration and validation
Unified error handling across all tools
Pluggable auth (none, jwt, oauth)
Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
Structured logging with optional OpenTelemetry tracing
STDIO and Streamable HTTP transports

FRED-specific:

Read-only access to the St. Louis Fed's FRED API (api.stlouisfed.org/fred)
Parallel multi-series fetching via Promise.allSettled with partial success reporting
DataCanvas spillover for multi-series or large observation results — spilled tables queryable via fedreserve_dataframe_query
Retry with backoff and 429 rate-limit detection against FRED's 120 req/min limit
FRED's native unit transformations delegated server-side for precision against the full series history

Getting started

Add the following to your MCP client configuration file. Obtain a free FRED API key at research.stlouisfed.org/docs/api/api_key.html.

config.json

{
  "mcpServers": {
    "federal-reserve-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/federal-reserve-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "FRED_API_KEY": "your-api-key"
      }
    }
  }
}

Or with npx (no Bun required):

config.json

{
  "mcpServers": {
    "federal-reserve-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/federal-reserve-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "FRED_API_KEY": "your-api-key"
      }
    }
  }
}

Or with Docker:

config.json

{
  "mcpServers": {
    "federal-reserve-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "-e", "FRED_API_KEY=your-api-key",
        "ghcr.io/cyanheads/federal-reserve-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 FRED_API_KEY=... bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

Bun v1.3.2 or higher.
A free FRED API key from stlouisfed.org. The key grants 120 requests/minute.

Installation

Clone the repository:

git clone https://github.com/cyanheads/federal-reserve-mcp-server.git

Navigate into the directory:

cd federal-reserve-mcp-server

Install dependencies:

bun install

Configure environment:

cp .env.example .env
# edit .env and set FRED_API_KEY

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts.

Variable	Description	Default
`FRED_API_KEY`	Required. API key from stlouisfed.org.	—
`FRED_BASE_URL`	Override the FRED API base URL.	`https://api.stlouisfed.org/fred`
`FRED_DATASET_TTL_SECONDS`	Sliding TTL for DataCanvas-registered observation tables (seconds).	`86400`
`FRED_DATAFRAME_DROP_ENABLED`	Set `true` to expose the `fedreserve_dataframe_drop` tool.	`false`
`CANVAS_PROVIDER_TYPE`	Set to `duckdb` to enable DataCanvas SQL querying for observation results.	—
`MCP_TRANSPORT_TYPE`	Transport: `stdio` or `http`.	`stdio`
`MCP_HTTP_PORT`	Port for HTTP server.	`3010`
`MCP_AUTH_MODE`	Auth mode: `none`, `jwt`, or `oauth`.	`none`
`MCP_LOG_LEVEL`	Log level (RFC 5424).	`info`
`LOGS_DIR`	Directory for log files (Node.js only).	`<project-root>/logs`
`STORAGE_PROVIDER_TYPE`	Storage backend.	`in-memory`
`OTEL_ENABLED`	Enable OpenTelemetry instrumentation.	`false`

See .env.example for the full list of optional overrides.

Running the server

Local development

Build and run:

# One-time build
bun run rebuild

# Run the built server
bun run start:stdio
# or
bun run start:http

Run checks and tests:

bun run devcheck   # Lint, format, typecheck, security
bun run test       # Vitest test suite
bun run lint:mcp   # Validate MCP definitions against spec

Docker

Terminal

docker build -t federal-reserve-mcp-server .
docker run --rm -e FRED_API_KEY=your-key -e MCP_TRANSPORT_TYPE=http -p 3010:3010 federal-reserve-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/federal-reserve-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Directory	Purpose
`src/index.ts`	`createApp()` entry point — registers tools and inits services.
`src/config`	Server-specific environment variable parsing and validation with Zod.
`src/mcp-server/tools`	Tool definitions (`*.tool.ts`). Eight tools across FRED domain and DataCanvas.
`src/services/fred`	FRED API service — HTTP client, retry, 429 handling, key injection.
`src/services/canvas-bridge`	DataCanvas adapter — table naming, TTL/provenance tracking, SQL gate extras.
`tests/`	Unit and integration tests mirroring `src/`.
`docs/`	Design and planning documents.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

Handlers throw, framework catches — no try/catch in tool logic
Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
Register new tools in src/mcp-server/tools/definitions/index.ts
Wrap FRED API calls: validate raw response → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.