Allergen Detector

io.github.daniellemeng1022由 GitHub 帳號 daniellemeng1022 發布v0.1.0更新於 Oct 26, 2026

根據每位家庭成員的過敏情況檢查食品和化妝品成分，包括隱藏名稱。

AI 翻譯由 AI 模型根據下方的原文描述翻譯，可能有誤。

原文描述

Checks food and cosmetic ingredients against each household member's allergies, incl. hidden names.

已驗證Streamable HTTP可網頁執行

概覽

Allergen Detector 的託管 MCP 服務（allergen-detector-mcp.onrender.com）；可選 API 金鑰；Streamable HTTP；3 個工具。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

端點
allergen-detector-mcp.onrender.com
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Allergen Detector，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.daniellemeng1022%2Fallergen-detector/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "allergen-detector": {
      "type": "http",
      "url": "https://allergen-detector-mcp.onrender.com/mcp"
    }
  }
}

README

Allergen Detector MCP

The Allergen Detector matching engine as an MCP server, so AI assistants and shopping agents (ChatGPT, Claude, and others) can check a product against a household's allergies before recommending or buying it.

It uses the same matcher.js and allergen map as the Chrome extension (51 allergens, 1,078 names). The map refreshes daily from GitHub, so map updates reach agents with no redeploy.

Tools

ToolWhat it does
check_product_allergensChecks an ingredient list against one or more people's allergens (with severity) and returns who is affected, by which ingredient, and why. "Free from" claims never hide a real ingredient.
lookup_ingredientTells which allergen an ingredient name belongs to ("sodium caseinate" → milk).
list_supported_allergensLists the allergens the service covers.

The same checks are also a plain web API for agents that don't use MCP: POST /api/check, POST /api/lookup and GET /api/allergens, described at /openapi.json.

API keys are optional. Set API_KEYS="muse=<key>,acme=<key>" on the host to give each partner its own key, sent as X-API-Key or Authorization: Bearer. Requests without a key still work; a wrong key gets a 401. A valid key names the partner in /stats.

All tools are read-only and stateless. Nothing about the person (allergens, ingredients) is stored or logged. The only log is an anonymous count of tool calls per day, for measuring traction.

Run it

bash
npm installnpm test           # end-to-end test over MCPnpm start          # remote server: http://localhost:3000/mcpnpm run stdio      # local server for Claude Desktop and similarnpm run sync       # copy the latest matcher.js and map from the extension

To use it locally in Claude Desktop, add this to the mcpServers section of its config:

json
"allergen-detector": { "command": "node", "args": ["/path/to/allergen-mcp/server.js", "--stdio"] }

Launch steps

  1. Host it at a public HTTPS URL. Render or Fly.io can run npm start from a GitHub repo for $0–7/month. Later, point mcp.safi.ai at it.
  2. Privacy policy and terms page. Every directory requires one. Until safi.ai is live, host it on GitHub Pages. Its main point: no health data is stored.
  3. List it in the official MCP Registry (registry.modelcontextprotocol.io) with the mcp-publisher CLI, under io.github.daniellemeng1022/allergen-detector. Many clients and directories pull from it.
  4. Submit to the community directories: Smithery, Glama, PulseMCP and mcp.so.
  5. Claude: anyone can add it today as a custom connector by pasting the URL. To appear in Anthropic's connectors directory, submit it through their directory form.
  6. ChatGPT: test it in developer mode, then submit it as an app through OpenAI's Apps SDK submission process. This needs a verified developer account.
  7. Meta Muse (do this first): submit at muse.ai/platform. Choose "Existing MCP," enter the hosted URL, choose "API keys" and give Meta a key from API_KEYS (e.g. muse=…) so its calls show up as muse in /stats and payments to "no," then describe the service. Meta tests the live endpoint, so step 1 has to be done first. Muse already shops at Sephora, Walmart, Best Buy and the Shopify catalog, which covers both of our categories (cosmetics and food).
  8. Instinct and similar assistants: Instinct doesn't document custom MCP support. It shops through Shopify and Shop Pay. Reach out for a partnership instead.
  9. Shopping agents: contact teams building agentic-commerce products and offer the endpoint free during a pilot.
  10. Measure: set STATS_KEY on the host, then open https://<your-url>/stats?key=<STATS_KEY> to see calls by day, agent and tool. A connect count is an agent connecting; tool counts are real checks. /stats resets when the server restarts, but every count is also a [usage] JSON line in the host's logs. Track weekly checks and the number of distinct agents.

Before scaling

  • Add rate limiting and an API key for heavy business users. Keep a free tier.
  • Keep the disclaimer in every response. Don't present results as medical advice.

來源：README.md，提交 3963d31

工具

3

check_product_allergens

Check a product for allergens

Check a product's ingredient list against the allergies of one or more people in a household. Catches allergens listed under other names (e.g. "arachis oil" for peanut, "casein" for milk, Latin plant names in cosmetics) and does not let "free from" claims hide a real ingredient. Covers food and cosmetics. Call this before recommending or buying a food, cosmetic or household product for someone with allergies.

輸入參數household必填ingredients必填product_name

lookup_ingredient

Look up an ingredient

Tell which allergens, if any, an ingredient name belongs to, e.g. "sodium caseinate" -> milk, "Prunus amygdalus dulcis oil" -> tree nuts, "DMDM hydantoin" -> formaldehyde releasers.

輸入參數ingredient必填

list_supported_allergens

List supported allergens

List the allergens this service can check (food and cosmetic), with the other names users may type for them.

無需輸入參數。

版本歷史

1
  1. v0.1.0最新Oct 26, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。