FRED API MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FRED_API_KEY | Yes | Your FRED API key from https://fred.stlouisfed.org/docs/api/api_key.html |
Instructions
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.
Capabilities
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_fred_series_observationsC | Get series observations from the Fred API. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of ambiguity or misselection. The tool's purpose is clearly defined and distinct by default.
The single tool name follows a clear snake_case verb_noun convention. With only one tool, the naming is trivially consistent.
One tool is too few for a server claiming to represent the FRED API, which has a broad range of endpoints. The apparent scope far exceeds what a single tool can cover.
The FRED API supports many resource types (series, categories, releases, sources, etc.) beyond just fetching observations. This server only exposes one observation endpoint, leaving the surface severely incomplete for the stated purpose.