Schema | fred-macro-mcp

fred-macro-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LOG_LEVEL`	No	Log verbosity.	WARNING
`FRED_API_KEY`	Yes	32-char FRED API key (required). Never logged.
`FRED_CACHE_BYPASS`	No	Force fresh reads while still writing.	false
`FRED_CACHE_BACKEND`	No	memory (zero-dep) or clickhouse (opt-in extra).	memory
`FRED_CACHE_ENABLED`	No	Opt-in read-through cache.	false
`FRED_CLICKHOUSE_URL`	No	DSN used only when backend is clickhouse.
`FRED_RATE_LIMIT_PER_MIN`	No	Client throttle (≤ FRED's 120/min ceiling).	120

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
get_seriesB	Return the observation series for a FRED economic data series. `series_id` is a FRED identifier (e.g. `GDP`, `CPIAUCSL`, `UNRATE`, `DGS10`). `start` / `end` optionally bound the window as ISO `YYYY-MM-DD` dates.
search_seriesA	Search the FRED catalog for series matching query keywords. Returns the most popular matches with their frequency, units, and observation range so an agent can pick the right `series_id`.
get_series_latestA	Return the single most-recent observation for a FRED series. Cheaper than `get_series` when an agent only needs the current value of a macro indicator.
get_release_calendarA	Return upcoming FRED data releases in the next days days. Useful for macro overlay: knowing when the next CPI / GDP / jobs print lands lets an agent flag event risk on the calendar.
health_checkA	Local health probe. Never calls FRED.
get_server_infoA	Local server metadata. Never calls FRED.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kevinkda/fred-macro-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server