Schema | FRED MCP Server

FRED MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HOST`	No	HTTP bind address (default is all interfaces).
`PORT`	No	HTTP port.	3000
`LOG_LEVEL`	No	error, warn, info, or debug (logs go to stderr).	info
`TRANSPORT`	No	Set to http for Streamable HTTP transport.	stdio
`FRED_API_KEY`	Yes	Your FRED API key. Required. You can obtain one from the FRED website (https://fred.stlouisfed.org/docs/api/api_key.html).
`MCP_BODY_LIMIT`	No	Maximum accepted JSON body size.	1mb
`MCP_MAX_SESSIONS`	No	Maximum concurrent MCP sessions (new sessions get 503 beyond this).	100
`FRED_CACHE_TTL_MS`	No	TTL for cached API responses (0 disables caching).	60000
`MCP_SESSION_TTL_MS`	No	Idle time before a session is reaped.	1800000
`FRED_API_TIMEOUT_MS`	No	Per-request timeout against the FRED API.	30000
`FRED_API_MAX_RETRIES`	No	Retries for 429/5xx/network failures (exponential backoff with jitter, honors Retry-After).	3
`FRED_CACHE_MAX_ENTRIES`	No	LRU cache capacity.	500
`FRED_RATE_LIMIT_PER_MINUTE`	No	Client-side token bucket matching FRED's per-key quota.	120
`FRED_API_RETRY_BASE_DELAY_MS`	No	Base delay for retry backoff.	500
`MCP_SESSION_SWEEP_INTERVAL_MS`	No	How often the idle-session reaper runs.	60000

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessNo issues