Data and API for Researchers, Risk Teams, and Engineers
Academic users already have FRED, OFR, and the NY Fed Consumer Credit Panel. The angle here is different: a single composite measuring U.S. household financial distress on a 0–100 scale, the same composite extended down to 3,144 counties, and 92 distress indicators wired through one consistent schema with cross-correlation results pre-computed. Free for any use, attribution required, MCP-queryable from your model.
Current ADI reading is 44.6 for 2025-Q4, band 3 of 5 (Typical). On average, its inputs sit higher than in 45% of their own quarterly histories since 2005.
MCP Endpoint
The full data layer is exposed as an MCP server — Anthropic's open standard for letting language models call tools. Any MCP-compatible client can query the indicators and county scorecards directly: Claude Desktop, Claude Code, Cursor, plus any in-house agent built on the MCP SDK. Read-only, rate-limited, auth-stub-ready for higher tiers, and free to install.
Install
Download the MCP server source files, install the Python dependencies, and add the server to your client's config. Full setup notes live in the MCP server README.
{
"mcpServers": {
"american-default": {
"command": "/absolute/path/to/venv/bin/python3",
"args": ["-m", "scripts.machine_layer.mcp_server"],
"cwd": "/absolute/path/to/american-default",
"env": {
"PYTHONPATH": "/absolute/path/to/american-default"
}
}
}
}Restart Claude Desktop. The five tools appear under the hammer icon. Other MCP clients (Cursor, in-house agents using the SDK) accept the same stdio invocation.
Tool surface
| Tool | Input | Returns |
|---|---|---|
get_indicator | slug (e.g. the-buffer) | Compact snapshot, pre-computed aggregates, canonical citation |
get_county_scorecard | fips (5-digit; 4-digit accepted) | CDI score, 5-domain breakdown, pre-baked citations |
get_adi_composite | — | Latest quarter, five domain scores, band + reading, citation |
search_indicators | query, optional limit (max 50) | Ranked matches with slug, branded name, category, URL |
get_cross_correlations | slug | Validated leading and lagging pairs split into as_leader + as_follower |
Every response carries schema_version: "v1". Breaking changes ship as new tools with a _v2 suffix; v1 stays live.
Worked example — cross-correlation from inside Claude
A risk modeler asks Claude (with the MCP server installed) to find indicators that lead the personal savings rate. Claude invokes get_cross_correlations with the savings-rate slug and synthesizes the response.
get_cross_correlations(slug="the-buffer"){
"schema_version": "v1",
"slug": "the-buffer",
"as_leader": [
{
"follower_slug": "the-pile-up",
"follower_name": "Mortgage + credit-card delinquency composite",
"optimal_lag_quarters": 9,
"raw_r": 0.69,
"crisis_validations": 3,
"granger_p": 0.001,
"oos_val_r": 0.62
}
],
"as_follower": [],
"citation": {
"news_copy": "American Default Research, American Distress Index..."
}
}
The same pattern works for any of the 92 indicators. Cross-correlation results came out of a five-filter scanner (FDR-corrected cross-correlation, first-differenced series, multi-crisis validation, Granger causality, out-of-sample validation) that tested 64,897 pair-lag combinations and produced 7 fully validated relationships. Methodology lives at /methodology/; the systematic results return as JSON at /api/research/leading-indicators.json.
Source: scripts/machine_layer/. Probe mode at python3 -m scripts.machine_layer.mcp_server --probe emits a JSON handshake and exits — useful for CI smoke tests.
Indicator Catalog
92 indicators across 9 categories — debt stress, buffer depletion, financial conditions, labor market, cost pressure, plus AWI workforce indicators and demographic context. Every indicator has its own page (live data, chart, source attribution, Wire-voice editorial), full historical JSON, downloadable CSV, and machine-readable citation files.
| Category | Indicators |
|---|---|
| Savings — How much financial cushion American households have left | 13 |
| Debt — Late payments, charge-offs, and total debt across credit cards, auto loans, student loans, and mortgages | 14 |
| Housing — Mortgage stress, foreclosures, and housing affordability | 8 |
| Jobs — Weekly layoff filings, monthly job numbers, wage growth, and who's hiring | 12 |
| Prices — How fast groceries, rent, gas, and healthcare are getting more expensive | 15 |
| Courts — Bankruptcy filings, consumer complaints, and what happens when people can't pay | 8 |
| Warning Signs — Surveys and financial signals that move before other stress measures | 8 |
| Who's Hurting — Food stamps, homelessness, and the demographics of who's falling through the cracks | 8 |
| AI & Work — AI capability, AI-linked layoffs, and labor-market exposure | 6 |
Per-indicator URLs
Substitute any indicator slug (e.g. the-buffer, auto-loan-delinquency-90-days, cpi-inflation-rate-all-items) for {slug} below. The full slug list is in the human-readable indicator index, the machine-readable /api/indicators.json, or the /llms.txt that LLMs hit on first contact.
| What | URL |
|---|---|
| Page | /indicators/{slug}/ |
| Full historical JSON | /api/indicators/{slug}.json |
| Full series CSV | /api/downloads/{slug}.csv |
| BibTeX citation | /citations/{slug}.bib |
| RIS citation (EndNote, Zotero) | /citations/{slug}.ris |
Browse the full indicator list at /indicators/. The /sources/ index groups indicators by federal publisher (FRED, BLS, NY Fed, Census, etc.) for users who think in publisher-units rather than topic-units.
Bulk Endpoints
When you want everything in one fetch — to load into a notebook, a backtest harness, or a model committee deck.
Endpoint What it contains /api/adi.jsonFull ADI quarterly history back to 2005-Q1: composite, band and band label, five domain scores, member percentiles /api/downloads/adi.csvSame content as CSV — one row per quarter /api/indicators.jsonAll 92 indicators with current value, trend, units, page URL, JSON URL, last update /api/downloads/all-indicators-latest.csvSame content as CSV — one row per indicator with the latest value /api/downloads/state-debt-statistics.csv51-state debt and delinquency metrics (mortgage, credit card, auto, student loan, HELOC) sourced from the NY Fed Consumer Credit Panel state release /api/research/leading-indicators.json7 fully validated leading-indicator relationships from the systematic five-filter scanner, plus the funnel statistics for every filter stage
County-level scorecards are best fetched one at a time via the MCP get_county_scorecard(fips) tool — the JSON payload is ~2.5 KB per county and the rate limiter is generous enough to walk the full 3,144-county set inside an hour from a single client. The scorecard JSON includes the composite score, all five domain scores, national and state ranks, and pre-baked citations. Source: get_county_scorecard.py in the MCP server.
A county-scorecard PDF (single-page, model-committee-ready, branded) is published for every county at https://pdf.americandefault.org/scorecards/{fips}.pdf. Useful when a stakeholder wants the data on paper instead of in JSON.
Methodology
The full ADI methodology lives at /methodology/adi/ — five domains (Delinquency, Default & Legal, Debt Burden, Labor, Safety Net & Buffer), each the mean of its member indicators' Hazen percentiles within their own full quarterly history, equal domain weights, and national band labels that always publish with the literal reading. The published history holds the global financial crisis at its peak (85.3 in 2009-Q3) and the stimulus era at the trough (15.7 in 2021-Q4). The page includes the production scoring rules, the replication code link, and citation templates.
The County Distress Index methodology is published as a PDF at /methodology/cdi-methodology.pdf — five equal-weighted domains, the current admitted indicator set, distress-oriented county percentiles, and geography labels expressed as ranks and fifths.
The systematic leading-indicator pipeline (cross-correlation + first differences + multi-crisis validation + Granger causality + out-of-sample) is documented inline at /methodology/#leading-indicators. The replication command is in the README at the repo root.
Citation
The license is permissive — Creative Commons Attribution 4.0. Use the data in commercial work, model committees, products, and journalism. Attribution is the only requirement. The canonical institutional name is American Default Research; the brand and URL is American Default; the composite is the American Distress Index (ADI); the county-level composite is the County Distress Index (CDI).
Templates for APA, MLA, Chicago, BibTeX, and news-copy short form are at /methodology/adi/#cite. Per-indicator BibTeX and RIS files are at /citations/{slug}.bib / .ris. The full canonical attribution block — including incorrect forms not to use — is at /llms.txt § Canonical Attribution.
FRED-derived series carry FRED's own attribution requirements (St. Louis Fed Terms of Use, including the no-AI-training clause). Downstream republishers should pass those through. Each indicator page lists its source attribution at the bottom; the per-indicator JSON and CSV downloads include it inline.
Talk to us about commercial use
Free with attribution covers virtually every use we have seen so far — research, journalism, product features that cite us, model-committee presentations. The form below is for anything that doesn't fit that shape: partnerships, embedded uses, white-label requests, custom data work, or a service-level arrangement on top of the free tier.
Or email partnerships@americandefault.org directly.