Skip to main content
Glama

Mhra Safety Alerts

mhra_safety_alerts
Read-onlyIdempotent

UK medicines and medical device safety alerts published by the MHRA on GOV.UK: Class 1-4 medicines recalls with affected batch numbers, Field Safety Notices from device manufacturers, device safety information, and National Patient Safety Alerts. Answers "has this medicine or device been recalled in the UK", "which batches were withdrawn", and "what safety alerts were issued last month". Returns each alert with its title, alert category, issue date, one-line summary and GOV.UK URL; filter by free text, category, issue-date range and clinical specialism.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 5,
      "issued_to": "2026-09-01",
      "issued_from": "2026-08-01"
    },
    "name": "mhra_safety_alerts"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo"newest_issued" (default) orders by the date MHRA issued the alert; "newest_published" orders by when the GOV.UK page went live. They differ, a weekly notice issued on the 31st can publish on the 9th of the next month.
limitNoAlerts to return, 1-100 (default 20).
queryNoFree-text search over alert titles and summaries, e.g. a medicine name ("fingolimod"), a manufacturer ("Zentiva") or a device type ("infusion pump").
offsetNoResults to skip, for paging (default 0).
issued_toNoLatest issue date, YYYY-MM-DD.
alert_typeNoRestrict to one alert category. One of: field-safety-notices, medicines-recall-notification, device-safety-information, national-patient-safety, mhra-safety-round-up.
specialismNoClinical specialism slug the alert is tagged for, e.g. "pharmacy", "dispensing-gp-practices", "medical-devices".
issued_fromNoEarliest issue date, YYYY-MM-DD.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / sort / description
      Previous value: -"\"newest_issued\" (default) orders by the date MHRA issued the alert; \"newest_published\" orders by when the GOV.UK page went live. They differ — a weekly notice issued on the 31st can publish on the 9th of the next month."New value: +"\"newest_issued\" (default) orders by the date MHRA issued the alert; \"newest_published\" orders by when the GOV.UK page went live. They differ, a weekly notice issued on the 31st can publish on the 9th of the next month."
  2. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent and open-world characteristics, so the bar is lower; the description adds return-shape information (title, category, issue date, one-line summary, GOV.UK URL) which matters because there is no output schema. It does not mention rate limits or result-set behaviour on empty queries, but it discloses enough behaviour beyond the annotations to be useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences: the first front-loads what the corpus is, the second states what it returns and how to filter, with illustrative example queries woven in. No filler, though the enumeration of alert categories makes the first sentence long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given eight optional parameters, full schema coverage and no output schema, the description supplies the missing piece (returned fields) and the query semantics an agent needs. Nothing essential to calling it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including a notably good explanation of sort ordering and the enum-like alert_type values, so the schema carries the parameter burden. The description only summarises the filter set ('free text, category, issue-date range and clinical specialism') and omits sort, limit and offset, adding little beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific resource (UK MHRA medicines and medical device safety alerts on GOV.UK) and enumerates its sub-categories (Class 1-4 recalls, Field Safety Notices, device safety information, National Patient Safety Alerts). An agent can tell it is a search/list tool over alerts rather than a detail or update tool, though it never names the sibling that fetches a full alert (mhra_alert_detail) to make the split explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete selection cues via the questions it answers ('has this medicine or device been recalled in the UK', 'which batches were withdrawn', 'what safety alerts were issued last month'), which makes the use case unambiguous. It stops short of explicit when-not-to-use guidance or naming alternative tools, so it is clear context but no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.