World Monitor
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.
Household recall checks over public CPSC, openFDA, EMA and EU Safety Gate data. No API key.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 7/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 7/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
用 Household Recall Watch 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Household Recall Watch,或回答中出现 Household Recall Watch 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Household Recall Watch
Household Recall Watch 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Household Recall Watch 的应用
B · 其他 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
Claude Code 暂时无法连接 Household Recall Watch
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Household Recall Watch 的应用
Cursor 暂时无法连接 Household Recall Watch
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Household Recall Watch 的应用
VS Code 暂时无法连接 Household Recall Watch
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Household Recall Watch 的应用
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
注册名称已通过 GitHub 账户 MGrin 验证,该账户拥有此仓库
代码最后更新于2个月前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/mgrin-household-recall-watch)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于2个月前,最新版本(0.2.1)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.
Manage monitors, status pages, incidents and maintenances in your openstatus workspace.
Validate oh-my-posh configurations and segment snippets against the official schema.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.
| 本项 Household Recall Watch | World Monitor | openstatus | Oh My Posh Validator | Strata | Jitsu | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 1/4 | 4/4 |
| 许可证 | MIT | AGPL-3.0 | AGPL-3.0 | MIT | Apache-2.0 | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A self-hosted Model Context Protocol server that lets a voice assistant answer household safety questions from public government recall data:
Every answer carries a short spoken sentence for the voice reply, plus structured detail with the source URL and date of every item. No API keys, no accounts, no LLM needed to run it.
Built for the Amazon Developer Hackathon, Alexa+ track. MCP spec 2025-11-25, Streamable HTTP, stateless, @modelcontextprotocol/sdk 1.30.1.
This is a simulated smart-display experience backed by a real MCP server; it has not been connected to an Alexa+ device. See the judge-run guide, the verification record and the friction log.
Not medical or safety advice. Recall and shortage data can be incomplete or late. Always check
the linked notice, and ask a pharmacist, doctor or the manufacturer before acting. Never stop a
prescribed medicine on your own.
Node 20 or newer. One process serves the MCP server at /mcp, the voice UI at / and the agent at POST /api/ask:
npm ci && npm start
Judge path.
npm start, open http://127.0.0.1:3000/. The badge reads *Scripted mode, no LLM*: a fixed phrase-to-tool mapping stands in for the model, but the MCP calls and the recall data are real and live. Try the suggestion chips, or drive it from the URL: http://127.0.0.1:3000/?q=Watch%20my%20crib%20mattress&q=Has%20anything%20in%20my%20house%20been%20recalled%3FOPENAI_API_KEY outside the repository and run npm start. The badge identifies the selected model (gpt-6-luna by default). This path was run live on 2026-10-02 with that model; other models were not exercised (EVIDENCE.md).Or Docker:
docker build -t recall-radar-mcp . && docker run --rm -p 3000:3000 recall-radar-mcp
docker run --rm -p 3000:3000 -e OPENAI_API_KEY recall-radar-mcp # with a model
| env | default | meaning |
|---|---|---|
PORT | 3000 | HTTP port |
HOST | 127.0.0.1 (0.0.0.0 in Docker) | bind address |
WATCHLIST_PATH | ./data/watchlist.json | where the household watchlist is stored; CPSC's last good responses are saved beside it as cpsc-cache.json |
ALLOWED_ORIGINS | *(none)* | extra browser Origins allowed besides localhost (comma-separated, * for any) |
MODEL_PROVIDER | openai if OPENAI_API_KEY is set, else scripted | openai, ollama or scripted |
OPENAI_API_KEY | *(none)* | OpenAI key; never logged or sent to the browser |
OPENAI_MODEL | gpt-6-luna | any Chat Completions model with function calling |
OPENAI_REASONING_EFFORT | none | sent as reasoning_effort; GPT-6 models refuse function tools on Chat Completions without none. Set omit for a model that rejects the field |
OPENAI_BASE_URL | https://api.openai.com/v1 | for an OpenAI-compatible gateway |
OLLAMA_URL / OLLAMA_MODEL | http://127.0.0.1:11434 / llama3.1 | Ollama's OpenAI-compatible endpoint (/v1/chat/completions) |
MCP_URL | this process's own /mcp | point the agent at another Recall Radar MCP server |
Endpoints: POST /mcp (MCP Streamable HTTP, stateless: no session id, no GET stream), GET /healthz, GET / (the UI), POST /api/ask ({"q": "...", "history": [...]}), GET /api/config, GET /api/watchlist. A stdio entry is also included: npm run start:stdio.
The stdio entry is listed in the MCP Registry as io.github.MGrin/household-recall-watch (server.json). Its package is an MCPB bundle attached to the GitHub release; npm run pack:mcpb rebuilds it and prints the SHA-256 that server.json must carry. The bundle keeps its watchlist at ~/.recall-radar/watchlist.json. Publishing is .github/workflows/publish-mcp.yml: on a v* tag (or gh workflow run publish-mcp.yml --ref vX.Y.Z) it checks the release bundle against server.json, then publishes with GitHub OIDC. Attach the bundle to the GitHub release before the workflow runs.
If your machine reaches the internet only through an HTTP proxy, Node's built-in fetch ignores HTTPS_PROXY unless you set NODE_USE_ENV_PROXY=1 (Node 24+). That applies to the OpenAI calls too.
The track allows *"a simulated Alexa+ experience in a web app"*; this is ours, named Recall Radar and using no third-party marks.
SpeechRecognition). Where that is missing the mic is disabled and the text box does the same job. Microphone behavior still needs a real-device check.speechSynthesis, with a mute toggle; a light bar along the bottom edge shows listening, thinking and speaking. Speaker output still needs a real-device check.?q=... asks on load; repeat it (?q=a&q=b) for a scripted walkthrough, and add mute=1 for silent capture.src/agent/)agent.ts is a real MCP client (SDK Client + StreamableHTTPClientTransport): per question it connects to /mcp, lists the tools, maps them to the model's function format and runs the tool-call loop, capped at 6 model steps. Tool results go back to the model as the tool's structuredContent. A ModelAdapter (types.ts) is one method: messages + tools in, text or tool calls out.
| adapter | status |
|---|---|
openai (openai.ts) | OpenAI Chat Completions with tools over plain fetch, no SDK. Unit-tested against recorded-shape responses, including a 3-step tool loop. Run against the live API with gpt-6-luna on 2026-10-02 (EVIDENCE.md). |
ollama | The same class pointed at Ollama's OpenAI-compatible endpoint. Untested: Ollama was not installed on the build machine. |
scripted (scripted.ts) | Deterministic: a few phrasings map to one tool call, and the reply is the tool's own spoken sentence (first item only). Used by the tests and the no-key demo. |
The system prompt (prompt.ts) keeps answers voice-first (two or three sentences: hazard, official remedy, what to do now), grounds every claim in a tool result, and forbids medical advice beyond the official remedy text.
MCP Inspector (no LLM key needed):
npx @modelcontextprotocol/inspector
In the Inspector UI choose transport Streamable HTTP, URL http://127.0.0.1:3000/mcp, Connect, then *Tools → List Tools* and call any tool.
From the terminal, with the bundled SDK client:
npm run call # list tools
npm run call -- search_product_recalls '{"query":"stroller","limit":3}' npm run call -- watchlist_add '{"name":"crib mattress","kind":"product"}' npm run call -- check_my_household '{}'
Eight tools. search_eu_product_recalls was added in v0.2.0, after the demo video was recorded; the video shows and says seven.
| tool | what it answers | sources |
|---|---|---|
search_product_recalls | "Has my stroller / space heater / crib been recalled?" | CPSC, openFDA device |
search_food_recalls | "Is there a recall on peanut butter?" "Any listeria recalls?" | openFDA food |
search_medicine_alerts | "Is my insulin recalled or short?" (region: us, eu, all) | openFDA drug, EMA shortages |
watchlist_add | "Keep an eye on my Graco stroller." (kind: product, food, medicine, any) | local file |
watchlist_list | "What am I watching?" | local file |
watchlist_remove | "Stop watching the stroller." | local file |
search_eu_product_recalls (v0.2.0) | "Was my USB charger recalled in the EU?" By product, brand, model or barcode (default: last 28 days, at most the 12 latest weekly reports) | EU Safety Gate |
check_my_household | "Has anything in my house been recalled?" (default: last 180 days) | CPSC, openFDA, EMA, by item kind (not Safety Gate) |
Each tool declares a zod input schema and an outputSchema; results come back as structuredContent (validated by the SDK) and as text. Each recall is normalised to:
{ source, id, title, hazard, remedy, date /* YYYY-MM-DD */, products[], url, summary /* one spoken sentence */ }
If one upstream is down, the others still answer and the result lists a warning; if every source for a question is down, the tool returns a clean MCP tool error (isError: true).
CPSC's API has answered some URLs and 503'd others, consistently per URL, for days at a time (seen 2026-10-02 to 10-04). So a CPSC read tries the window's own URL, then the same window without the product filter, then up to three EARLIER start dates (the 1st of the month, the 1st of the month before, a few dates that answered during the outage), and filters the rows here to the requested window: at most 6 requests in 20 seconds. When an earlier URL served the answer, the result says so in notes, naming that URL. Every good CPSC response is also saved beside the watchlist (cpsc-cache.json, the last 8 URLs, each with its fetch time). If every live attempt fails, the rows of the freshest saved copy that fall inside the window are served, each summary ending "From a saved copy of CPSC data fetched ; CPSC could not be reached live", and a warning names the fetch time; with no saved copy, CPSC is reported unavailable. Nothing else is invented.
Every upstream request has a 10-second timeout (20 seconds for Safety Gate). The EMA file is cached for an hour in memory, because EMA rate-limits repeated downloads. Safety Gate publishes one weekly report every Friday, each about 200-300 KB and 3-6 seconds to serve (2026-10-02): a search reads at most 12 reports, four at a time, caches the index for an hour and each published report for the life of the process. A cold four-week search took about 5 seconds; a repeat answers from the cache. When the window holds more than 12 reports, since in the answer is the oldest report actually read.
| source | endpoint | terms |
|---|---|---|
| US Consumer Product Safety Commission | saferproducts.gov/RestWebServices/Recall | US government work, public domain |
| openFDA enforcement reports (food, drug, device) | api.fda.gov/{food,drug,device}/enforcement.json | public domain / CC0 per open.fda.gov/license; openFDA's own disclaimer: do not rely on it for medical-care decisions. Keyless use is rate-limited (terms). |
| European Medicines Agency, medicine shortages catalogue | ema.europa.eu/en/documents/report/shortages-output-json-report_en.json | reuse permitted with EMA acknowledged as the source (legal notice); every EMA item carries its EMA URL |
| European Co