MCP server exposing US macroeconomic indicators - inflation, employment, growth, housing, rates and recession signals - from the Federal Reserve's FRED database.
Eight tools with clear verb-noun naming (list_, get_, compare_, search_) and comprehensive descriptions (100-250 chars each). All tools have documented input schemas with types and descriptions. Output schemas are well-structured with metadata fields. Error handling returns actionable guidance ('Call list_indicators to see valid names'). Main gaps: no enum constraints on category/period parameters, no explicit output schema documentation in docstrings, and missing parameter validation details (e.g., date format YYYY-MM-DD stated in description but not in schema format field).
Compare two or more indicators over the same period, for questions like "did wage growth beat inflation" or "how do the 2-year and 10-year yields compare".
Get the historical time series for one indicator.
Get the latest value of one economic indicator, with its recent changes already calculated.
List every US economic indicator this server provides. Call this first to discover valid indicator names before using the other tools.
Take a whole-economy snapshot: the latest reading of every headline indicator, all in one call.
Check the major recession warning signals: the yield curve, unemployment trend, and leading economic index.
Parameter 'category' in list_indicators lacks enum constraint. Description lists valid values as prose ('inflation, employment, growth...') instead of formal enum. LLMs may hallucinate invalid categories.
Parameter 'period' in compare_indicators lacks enum constraint. Valid values ('1y', '2y', '5y', '10y') stated in description but not in schema. LLMs may pass invalid periods like '3y' or '6m'.
Output schemas not documented in tool docstrings. While code returns structured dicts with metadata (name, title, category, units, frequency, series_id, source), the docstrings do not specify what fields the LLM should expect. This forces LLMs to infer structure from examples.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 62 | <=2025-11-25 | v2 |
Show which US economic data releases are scheduled over the coming days, for questions like "what economic data comes out this week".
Search for indicators by keyword, for questions like "show me all housing indicators" or "find anything about wages".
Date format constraints (YYYY-MM-DD) stated in parameter descriptions but not enforced in schema. No regex pattern or format field in JSON Schema. Validation happens at runtime, not at schema parse time.
No pagination support in tools returning lists (list_indicators, search_indicators, release_calendar). If indicator catalog grows large, responses could exceed context limits. No limit parameter on list_indicators; search_indicators has limit but no offset/cursor.