fred-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FRED_API_KEY | Yes | Your FRED API key |
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 |
|---|---|
| search_seriesA | Search for economic data series by text query. Args: query: The search text (e.g., "gdp", "unemployment"). limit: Maximum number of results to return in preview (default: 10). offset: Number of results to skip (default: 0). file_path: Optional absolute path to save the full search results as JSON. |
| get_series_infoB | Get metadata for a specific data series. Args: series_id: The ID of the series (e.g., "GDP", "UNRATE"). |
| get_series_dataA | Get data points for a specific series. Args: series_id: The ID of the series (e.g., "GDP"). limit: Max data points to return in the markdown preview (default: 1000). offset: Data points to skip (default: 0). file_path: Optional absolute path to save the full data as JSON. If provided, the full dataset (ignoring limit/offset) is saved and response is minimized. |
| get_category_detailsB | Get details for a specific category (if supported). Args: category_id: The ID of the category (e.g., 125). |
| get_category_childrenA | Get child categories for a specific category. Args: category_id: The parent category ID. |
| get_category_seriesA | Get series in a specific category. Args: category_id: The category ID. limit: Max results in preview. offset: Offset for preview. file_path: Optional absolute path to save the full list as JSON. |
| get_releasesB | Get all releases of economic data. Args: limit: Max results in preview. offset: Offset for preview. file_path: Optional absolute path to save the full list as JSON. |
| get_release_seriesB | Get series in a specific release. Args: release_id: The release ID. limit: Max results in preview. offset: Offset for preview. file_path: Optional absolute path to save the full list as JSON. |
| get_sourcesB | Get all sources of economic data. Args: file_path: Optional absolute path to save the sources list as JSON. |
| get_sourceB | Get details for a specific source. |
| search_related_tagsB | Get related tags for a set of tags. Args: tag_names: Semicolon separated list of tag names. limit: Max results. offset: Offset. |
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 11 tools
Each tool targets a distinct resource or action: series search, metadata, data, categories, releases, sources, and related tags. Even similar pairs like get_sources and get_source are clearly differentiated by list vs single-item semantics.
All tool names follow a consistent snake_case verb_noun pattern. Search operations use search_ and data retrieval operations use get_, which is a predictable and semantically meaningful convention.
11 tools is well-scoped for an economic data server, covering search, metadata, observations, categories, releases, sources, and tags without excessive fragmentation or redundancy.
The tool surface covers the core FRED workflows: discovering series, browsing categories/releases/sources, fetching metadata and observations. Minor gaps exist around tag browsing and direct series-to-tag relationships, but these do not break typical usage.