Skip to main content
Glama

식약처 허가 제품 검색

search_products
Read-onlyIdempotent

Find Korean MFDS-approved medical devices and drugs by product, model, company, permit number, name, or ingredient, returning identifiers for authorization checks and product comparisons.

Instructions

식약처 허가를 받은 의료기기·의약품을 찾아 식별자(get_permit의 id)를 돌려준다. 의료기기 by: product(품목명, 분류 이름 예: 체온계) / model(모델명, 대소문자 구분) / company(업체명) / permit_no(품목허가번호 예: 수인 26-4414 호). 기본 product. 의약품 by: name(제품명) / company(업체명) / ingredient(주성분 영문명 예: Acetaminophen) / permit_no(품목허가번호). 기본 name. 모두 부분 일치로 찾는다. 의료기기를 브랜드로 찾을 때는 model이나 company를 쓴다. 의약품 주성분은 영문명으로 저장되어 있다. 한글 성분명은 by=name으로 찾으면 제품명에 성분명이 들어간 제품이 나온다. 식약처 API 응답이 10~20초 걸릴 수 있다.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "query": "<query>"
    },
    "name": "search_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNo검색 기준. 종류별 허용 값은 도구 설명 참조
pageNo페이지 번호, 기본 1
typeYesdevice = 의료기기(사용목적 기준), drug = 의약품(효능효과 기준)
limitNo페이지당 건수, 기본 10
queryYes검색어

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond readOnly/idempotent/openWorld annotations, it discloses partial-match semantics, that ingredients are stored in English, and a 10-20s upstream API latency — operationally useful context an agent cannot get from the schema. Return shape is only sketched ("identifiers"), so not a full 5.

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?

Purpose and return value are front-loaded, then criteria are enumerated in a scannable per-type structure. A few lines (the Korean ingredient-name workaround) are slightly wordy but carry non-obvious guidance.

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

Completeness4/5

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

For a 5-parameter, two-enum, no-output-schema search tool, the definition covers type-dependent criteria, matching mode, defaults, and latency. Only the response shape (beyond "id") and pagination behavior are left implicit.

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

Parameters5/5

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

Although schema coverage is 100%, the schema only lists the `by` enum without saying which values are valid for device vs drug; the description supplies that mapping plus examples for each value. It also clarifies the default values per type, which adds real meaning beyond the structured fields.

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

Purpose5/5

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

The first line states a specific verb and resource (find MFDS-approved medical devices and drugs) and the return value (identifiers usable as get_permit's id). It is clearly distinguishable from siblings compare_products and get_permit by scope.

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 guidance on which `by` value to pick per product type, and explicitly says to use model or company when searching devices by brand. It does not explicitly state when to prefer this over compare_products, but guidance within the tool's own decision space is clear.

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

Deploy Server

Other Tools