epitaxy

Federal drug shortages and recalls joined to the federal contracts that buy those drugs.

我该使用它吗

质量与安全性

A
描述质量
96%
模式完整度
65%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~483token 数(工具定义)
~440 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.38%)

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": {
    "epitaxy": {
      "command": "uvx",
      "args": [
        "epitaxy-mcp"
      ]
    }
  }
}

可运行的软件包

pypiepitaxy-mcp0.1.4stdio

远程端点

https://drugs.crossgrain.xyz/v1/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_data_freshness

Returns when the data was last activated, how many segments are live, and the state of the last run. Call this first when you need to know whether the data is fresh.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢list_drug_shortages(status, generic_name, company_id, limit)

Current and resolved US drug shortages as reported by the FDA. Each row carries the generic name, the reporting company and its company_id. Filters: status, generic_name, company_id, limit.

输入模式

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "description": "for example Current or Resolved"
    },
    "generic_name": {
      "type": "string"
    },
    "company_id": {
      "type": "string"
    },
    "limit": {
      "type": "integer"
    }
  }
}
🟢list_drug_recalls(classification, company_id, limit)

FDA drug recalls and enforcement reports. Filters: classification (Class I, II, III), company_id, limit.

输入模式

{
  "type": "object",
  "properties": {
    "classification": {
      "type": "string"
    },
    "company_id": {
      "type": "string"
    },
    "limit": {
      "type": "integer"
    }
  }
}
🟢list_federal_drug_contracts(agency, company_id, limit)

US federal contracts for drugs, product service code 6505, from USAspending. Filters: agency, company_id, limit.

输入模式

{
  "type": "object",
  "properties": {
    "agency": {
      "type": "string"
    },
    "company_id": {
      "type": "string"
    },
    "limit": {
      "type": "integer"
    }
  }
}
🟢get_supplier_exposure(award_id, company_id, min_confidence, limit)

The join: a federal contract whose supplier has an FDA shortage or recall. Every row carries company_name, confidence (exact, probable or weak) and match_method. A cross source join is NEVER exact, because FDA and USAspending share no identifier. The claim is: this government supplier has an active FDA shortage or recall. It does NOT claim that this contract delivers that drug. Without a key you get exact and probable matches only, at most 20 rows, without the evidence field.

输入模式

{
  "type": "object",
  "properties": {
    "award_id": {
      "type": "string",
      "description": "federal award identifier"
    },
    "company_id": {
      "type": "string"
    },
    "min_confidence": {
      "type": "string",
      "enum": [
        "probable",
        "weak"
      ],
      "description": "weak needs a paid key"
    },
    "limit": {
      "type": "integer"
    }
  }
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具
已验证未记录版本5 个工具
已验证未记录版本5 个工具