# American Default Research [Verified] [Health: Active]

**Category:** 💰 Finance & Fintech  
**Repository:** https://github.com/vibecode1/american-default-mcp  
**GitHub Stars:** 0  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/american-default-research-2

## Description
Six read-only research tools for U.S. household financial distress, the American Distress Index (ADI), and county scorecards. Journalists, researchers and AI agents can retrieve compact indicator snapshots with source citations, search indicators, compare county scores, and inspect published cross-indicator relationships. Includes the versioned get_indicator_v2 tool with comparison-safety fields. Free hosted Streamable HTTP access; no API key required. Anonymous access is limited to 10 calls per minute and 60 per hour per IP block.

## Tools
Capabilities this server exposes over MCP:

- **get_indicator** — Fetch a compact snapshot of an American Default economic indicator by slug. Returns latest value, unit, frequency, direction, pre-computed aggregates (period averages, extremes, sustained runs), editorial prose (when available), and canonical APA / MLA / Chicago / news-copy citations. Raw historical series is NOT included — use https://americandefault.org/api/indicators/{slug}.json for the full data. Slug examples: 'the-buffer' (personal savings rate), 'mortgage-delinquency-rate', 'initial-unemployment-claims-sa'.
- **get_indicator_v2** — Fetch an explicitly versioned compact indicator snapshot. Returns the latest value and canonical citation plus `trend_suppressed` and `series_breaks` comparison-safety fields. Callers must pass `response_version='v2'`; unsupported versions fail closed. The legacy `get_indicator` tool remains pinned to its original v1 shape.
- **get_county_scorecard** — Fetch a county's County Distress Index (CDI) scorecard by 5-digit FIPS code. Returns the 0-100 score (the share of the other U.S. counties with a lower composite, rounded down; field composite_score), score label, national + state rank (national_rank_ordinal is filled only for the top and bottom 100, where the site prints it), 5-domain breakdown (Delinquency, Default & Legal, Debt Burden, Labor, Safety Net & Buffer), key findings, and pre-baked APA / MLA / Chicago / news-copy citations. Accepts 4-digit FIPS with implicit leading zero. 3,144 counties available.
- **get_adi_composite** — Fetch the latest quarterly reading of the American Distress Index (ADI) composite. Returns the composite score (0-100), band (1-5) with its label, the composite's rank in its own published history (rank_in_history.reading: quote this beside the band label), the methodology reading of the inputs, and the five-domain breakdown (Delinquency, Default & Legal, Debt Burden, Labor, Safety Net & Buffer) with domain scores and member component percentiles. Updated quarterly.
- **search_indicators** — Search the 121-indicator registry by keyword. Returns ranked matches (up to `limit`, default 10, max 50) with slug, branded name, underlying name, category, and canonical URL. Scoring is substring+prefix over slug, branded_name, name, and category — e.g. query 'savings' returns both The Buffer (personal saving rate) and The Safety Net (emergency savings survey). Use this when you want to discover which slug corresponds to a concept before calling `get_indicator`.
- **get_cross_correlations** — Fetch statistically-validated leading/lagging relationships for an indicator. Source: the five-filter leading-indicator scanner (cross-correlation → first-differenced CCF → multi-crisis validation → Granger causality → out-of-sample validation). Returns two lists: `as_leader` (pairs where this indicator precedes its follower) and `as_follower` (pairs where another indicator precedes this one). Only fully-validated pairs are included — partial matches are not surfaced. Most of the 121 indicators return empty lists; only a handful of pairs clear the full gauntlet.

## Claude Desktop Quick Installation
No confirmed install details yet, so no config is published. Follow the setup steps in the repository above.

## Documentation

## What American Default Research does

American Default Research exposes six read-only research tools for studying U.S. household financial distress. Its data covers economic indicators, county scorecards, the American Distress Index (ADI), and statistically validated relationships between indicators. Results are designed as compact research snapshots rather than unrestricted database access, and include dates, original publishers, and citation formats such as APA, MLA, Chicago, and news copy when applicable.

The indicator registry contains 121 entries. Individual snapshots can include the latest value, unit, reporting frequency, direction, period averages, extremes, sustained runs, and editorial text. Historical series are not returned by the MCP indicator tools; where available, full histories can be accessed from the corresponding public JSON endpoint.

## How it works

The hosted service uses Streamable HTTP at `https://mcp.americandefault.org/mcp`. A compatible MCP client sends tool calls to that endpoint, so normal use does not require a local process, account, API key, data download, or conversation history. Anonymous requests are limited to 10 calls per minute and 60 calls per hour per IP block. Higher-volume access can be requested through the public documentation, while static JSON endpoints are intended for permitted bulk downloads.

The service validates inputs and returns errors for invalid indicator slugs or county codes instead of generating substitute results. County lookups use FIPS codes, including four-digit values that receive an implicit leading zero. The `/up` path provides a hosted HTTP health endpoint.

## Setup and configuration

Add the hosted endpoint as a custom MCP connection in a compatible client. Cursor configuration uses the following structure:

```json
{
  "mcpServers": {
    "american-default-research": {
      "url": "https://mcp.americandefault.org/mcp"
    }
  }
}
```

Cline requires the transport to be stated explicitly:

```json
{
  "mcpServers": {
    "american-default-research": {
      "type": "streamableHttp",
      "url": "https://mcp.americandefault.org/mcp"
    }
  }
}
```

Claude can connect through its custom connector settings. Cloning the public repository alone does not create a complete local data installation; the hosted endpoint is the normal connection method.

## Tools and capabilities

- `search_indicators` finds registry entries by substring and prefix matches across slugs, names, and categories. Results include public URLs and can be limited to 50 matches.
- `get_indicator` returns the legacy v1 compact snapshot for a selected slug.
- `get_indicator_v2` requires `response_version: "v2"` and adds comparison-safety fields such as `trend_suppressed` and `series_breaks`. Use it when comparing readings.
- `get_county_scorecard` returns a county’s 0–100 composite score, rankings, five domain scores, findings, and citations for one of 3,144 counties.
- `get_adi_composite` returns the latest quarterly ADI reading, band, historical rank, methodology context, and five-domain breakdown.
- `get_cross_correlations` returns only relationships that pass the service’s full validation process. Empty results are normal for many indicators.

## Limitations and notes

The tools are read-only and do not expose private homeowner records, arbitrary SQL, the underlying warehouse, or financial transactions. The ADI describes current conditions and does not forecast outcomes. Treat indicator comparisons carefully: v2 can flag suppressed trends and series breaks, and historical indicators are not presented as current. Full historical data, when available, must be retrieved separately from the public indicator JSON endpoint. Attribution to American Default Research is requested, and source data remains subject to each publisher’s terms.

_Full upstream README: https://allmcps.com/mcp/american-default-research-2/readme_