How do I connect an AI agent to Product safety & recalls?

Use the MCP streamable HTTP endpoint https://fourzerotwo.si/mcp/v/safety-recalls.

Catalog › si.fourzerotwo/safety-recalls

Is Product safety & recalls reliable?

Being measured Measurement in progress: 2 check(s) so far. A verdict needs at least 3 checks.

Last check: 2026-10-12 00:35 UTC · answered in 8005 ms · remote (no install)

En français : Mesure en cours. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

UK product recalls, MHRA drug and device alerts, FSA food alerts, accident reports and US CPSC…

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "safety-recalls": {
      "url": "https://fourzerotwo.si/mcp/v/safety-recalls"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"si.fourzerotwo/safety-recalls"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Real task being tested — Faceabot asked uk-food-hygiene__search to do a small read-only task 1 time(s): 0 returned a real result. Last result: tool_error (its schema declares no required input, so Faceabot sent {}; the tool answered with an error, so it probably needs inputs its schema does not declare) in 4292 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-12 00:35 UTC	❌ timeout		8005 ms
2026-10-11 18:31 UTC	✅ ok	❌ tool_error	10012 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

fourzerotwo Reliable (measured) · 100% over 28 checks Does the job (tested) · 27/28

400+ data APIs for agents: UK companies, property, trade, tenders, recalls, sanctions. Free tier

MCP endpoint : https://fourzerotwo.si/mcp · website · measurements and details

Environment & energy Flaky · 80% over 5 checks Fails real tasks · 0/4

UK river levels and rainfall, bathing waters, flood warnings, weather, earthquakes and the GB…

MCP endpoint : https://fourzerotwo.si/mcp/v/environment · website · measurements and details

Health & medicines Reliable (measured) · 100% over 26 checks Fails real tasks · 0/26

Clinical trials, RxNorm drug lookups, FDA drug and device data, PubMed and NHS organisations.

MCP endpoint : https://fourzerotwo.si/mcp/v/health · website · measurements and details

Research papers Being measured · 50% over 2 checks Real task being tested · 0/1

arXiv, PubMed, Crossref and OpenAlex scholarly metadata.

MCP endpoint : https://fourzerotwo.si/mcp/v/research · website · measurements and details

Everyday agent tools Flaky · 67% over 3 checks Real task being tested · 2/2

Time zones and world business days, VAT rates and maths, currency conversion, UK business days…

MCP endpoint : https://fourzerotwo.si/mcp/v/tools · website · measurements and details

Publisher of Product safety & recalls?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/si.fourzerotwo/safety-recalls.svg)](https://faceabot.com/tools/si.fourzerotwo/safety-recalls)

Data in JSON: /api/catalog?id=si.fourzerotwo/safety-recalls · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms