Epitaxy

xyz.crossgrain由 crossgrain.xyz 发布官方发布者v0.1.4更新于 Oct 24, 2026

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

已验证Streamable HTTP可网页运行数据与分析商业与电商

概览

AI 生成的概览

Epitaxy 将 FDA 药品短缺与召回数据与美国联邦药品合同关联,让助手查询存在短缺或召回风险的供应商。

可以做什么
查询数据新鲜度、活跃分段数量与最近一次运行状态,判断结果是否可信。列出当前及已解决的 FDA 药品短缺,可按状态、通用名或公司筛选。列出 FDA 药品召回与执法报告,可按分类或公司筛选。列出 USAspending 中产品服务代码 6505 的美国联邦药品合同,可按机构或公司筛选。获取供应商风险记录,将联邦合同与存在 FDA 短缺或召回的供应商关联,每行附带置信度与匹配方式。
适用场景
适合调查医药供应链风险、政府供应商的药品短缺或召回暴露,或联邦药品采购情况,并希望直接获得带明确置信度的关联结果而非原始数据。
运行要求
可作为远程 streamable HTTP 端点使用,也可通过 PyPI 包 epitaxy-mcp 以 stdio 本地运行(用 uvx 启动)。免费层无需注册或密钥;可选的 EPITAXY_API_KEY 用于付费层。EPITAXY_API_URL 可覆盖默认基础地址。需要能访问该 API 主机的网络。
安装前请注意
免费层最多返回 20 行,不含 evidence 字段与 weak 匹配,数据延迟 24 小时。跨源关联永远不会是 exact,使用前须阅读置信度(exact、probable、weak)。付费方案涉及费用(月度订阅、按次 USDC 支付或一次性批量购买);API 密钥属于机密信息。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Epitaxy,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/xyz.crossgrain%2Fepitaxy/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "epitaxy": {
      "type": "http",
      "url": "https://drugs.crossgrain.xyz/v1/mcp"
    }
  }
}

README

epitaxy

mcp-name: xyz.crossgrain/epitaxy

Federal drug shortages and recalls, joined to the federal contracts that buy those drugs. One call, no signup.

What it claims: this government supplier has an active FDA shortage or recall. What it does not claim: that a specific contract supplies a specific drug. Federal contract descriptions average 47 characters and almost never name the drug, so we say so instead of pretending otherwise.

Try it now, no key

bash
curl https://drugs.crossgrain.xyz/v1/exposure?limit=5

One row of the answer, shortened:

json
{"exposure_id": "0026624dec7b6d9f", "award_id": "SPE2DP25F109W", "company_id": "a4fdd4a7530f4962", "company_name": "TEVA PHARMACEUTICALS USA, INC.", "company_key": "teva pharmaceuticals usa", "shortage_id": "022c478fb3af28c4", "confidence": "probable", "match_method": "company_name_normalized"}

MCP

Remote, nothing to install:

json
{ "mcpServers": { "epitaxy": { "url": "https://drugs.crossgrain.xyz/v1/mcp" } } }

Local, stdio:

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

Tools: get_data_freshness, list_drug_shortages, list_drug_recalls, list_federal_drug_contracts, get_supplier_exposure.

Read the confidence field, always

valuemeaning
exactmatch on a shared identifier, here an NDC inside FDA data
probablenormalized company name, or a drug name token in the contract text
weakanything softer, an indication only

Matching on both company and drug at once is not promoted to exact. Cross source joins are never exact, because FDA and USAspending share no identifier. Anyone claiming otherwise has a different source or is guessing.

Free tier

Works forever, no key, no signup. Returns at most 20 rows, without the evidence field, without weak matches, and with data delayed by 24 hours. Nothing is stored: no counters, no IP addresses. If a version that old does not exist yet, you get the oldest one available, so the free tier is never empty while data exists.

Addressing

These two addresses are the same segment and both work permanently:

https://drugs.crossgrain.xyz/v1/exposurehttps://drugs.crossgrain.xyz/drugs/v1/exposure

Later segments arrive as /devices/v1/..., /food/v1/... and so on. A path whose segment is reserved but not live yet answers 404 with segment_not_live, it never returns another segment's data. An address that has been published is never withdrawn.

Paid

planpricecontents
Starter29 USD/mo10 000 calls
Pro99 USD/mo100 000 calls plus daily delta feed
x4020.004 USD/callUSDC on Base, no signup
Bulk dump199 USDone off, Stripe only

Sources and licence

  • openFDA, public domain, CC0 1.0 Universal
  • USAspending, public domain, code under CC0

Data is unvalidated and must not be used for medical decisions. This project is MIT licensed. Docs: https://drugs.crossgrain.xyz/docs

来源:README.md,提交 934d45b

工具

5

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.

无需输入参数。

list_drug_shortages

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.

输入参数limitstatuscompany_idgeneric_name

list_drug_recalls

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

输入参数limitcompany_idclassification

list_federal_drug_contracts

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

输入参数limitagencycompany_id

get_supplier_exposure

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.

输入参数limitaward_idcompany_idmin_confidence

版本历史

1
  1. v0.1.4最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分