# American Default Research

> Read-only MCP for U.S. household distress: 96 indicators, ADI composite, 3,144 counties.

- name: org.americandefault/research
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 89/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/org.americandefault%2Fresearch
- tools: https://api.protogrid.dev/v1/servers/org.americandefault%2Fresearch/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "research": {
      "type": "http",
      "url": "https://mcp.americandefault.org/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-162d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,395 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 1,395 tokens to load them all
- tool set hash: edff81537cea008606db6484d667dbaf
- badge: [![protogrid quality](https://protogrid.dev/badge/org.americandefault/research.svg)](https://protogrid.dev/servers/org.americandefault/research)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.americandefault.org/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `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 and the literal reading gloss, the composite's own rank in history, and the five-domain breakdown (Delinquency, Default & Legal, Debt Burden, Labor, Safety Net & Buffer) with domain scores and member component percentiles. Updated quarterly.
- `get_county_scorecard`: Fetch a county's County Distress Index (CDI) scorecard by 5-digit FIPS code. Returns composite score (0-100), score label, national + state rank, 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_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 103 indicators return empty lists; only a handful of pairs clear the full gauntlet.
- `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', '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.
- `search_indicators`: Search the 103-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`.