American Default Research

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

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
88%
命名质量
100%
投毒风险
80%
权限匹配度
100%
协议合规性
100%

发现(2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 get_indicator 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,383token 数(工具定义)
~1.0 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.08%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "research": {
      "url": "https://mcp.americandefault.org/mcp"
    }
  }
}

远程端点

https://mcp.americandefault.org/mcpstreamable-http

它能做什么

工具清单

工具(6)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_indicator(slug)

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'.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "The kebab-case indicator slug (e.g., 'the-buffer' for personal savings rate, 'mortgage-delinquency', 'initial-unemployment-claims-sa'). 103 indicators available. Use `search_indicators` first to discover which slug corresponds to a concept.",
      "title": "Slug",
      "type": "string"
    }
  },
  "required": [
    "slug"
  ],
  "title": "_get_indicatorArguments"
}
🟢get_indicator_v2(slug, response_version)

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.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "The kebab-case indicator slug (e.g., 'the-buffer' or 'the-pinch'). Use `search_indicators` to discover slugs.",
      "title": "Slug",
      "type": "string"
    },
    "response_version": {
      "const": "v2",
      "description": "Required explicit response contract version. The only supported value for this tool is 'v2'.",
      "title": "Response Version",
      "type": "string"
    }
  },
  "required": [
    "slug",
    "response_version"
  ],
  "title": "_get_indicator_v2Arguments"
}
🟢get_county_scorecard(fips)

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.

输入模式

{
  "type": "object",
  "properties": {
    "fips": {
      "description": "The 5-digit numeric county FIPS code as a string (e.g., '13063' for Clayton County, GA). 4-digit values are zero-padded internally. 3,144 counties available.",
      "title": "Fips",
      "type": "string"
    }
  },
  "required": [
    "fips"
  ],
  "title": "_get_county_scorecardArguments"
}
🟢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.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "_get_adi_compositeArguments"
}
🟢search_indicators(query, limit)

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`.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "The keyword to search (e.g., 'savings', 'mortgage', 'inflation'). Scoring runs substring + prefix matching over slug, branded_name, name, and category fields.",
      "title": "Query",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Max number of ranked matches to return. Default 10. Hard cap 50 (values above are clamped). Values above 1000 are rejected as abuse.",
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "_search_indicatorsArguments"
}
🟢get_cross_correlations(slug)

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.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "The kebab-case indicator slug to look up (e.g., 'the-buffer', 'initial-unemployment-claims-sa'). Returns split lists of pairs where this indicator is the leader vs the follower. Empty lists are common — only fully-validated pairs surface.",
      "title": "Slug",
      "type": "string"
    }
  },
  "required": [
    "slug"
  ],
  "title": "_get_cross_correlationsArguments"
}

推荐提示词

search_research
Search for information about [topic] using American Default Research
预期工具: search_indicators
find_specific
Find [specific item] using American Default Research
预期工具: search_indicators
retrieve_data
Get details about [item] from American Default Research
预期工具: get_indicator
fetch_info
Fetch [information type] using American Default Research
预期工具: get_indicator
research_workflow
Search for [topic], then get detailed information about the top results using American Default Research
预期工具: search_indicatorsget_indicator

社区

评价此服务器

证据

最近观测

已验证未记录版本6 个工具
已验证未记录版本6 个工具