This MCP server provides access to the Korea Pharmaceutical Information Center (KPIC) drug database through two complementary tools:
Search drugs by name - Find medications using Korean or English drug names (partial or full), returning basic information including drug name, manufacturer, efficacy, and dosage instructions for multiple matching results
Get detailed drug information - Retrieve comprehensive details for a specific drug using its unique drug code (obtained from search results), including ingredients, additives, storage methods, precautions, contraindications, and information for pregnant/nursing mothers
Two-step lookup workflow - First search broadly by name to find relevant medications, then drill down using specific drug codes for complete pharmaceutical data from Korea's official pharmaceutical information authority
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@KPIC MCP Server search for detailed information about Tylenol"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
약학정보원(Korea Pharmaceutical Information Center) API를 위한 Model Context Protocol (MCP) 서버입니다.
이 MCP 서버는 약학정보원의 의약품 정보를 조회할 수 있는 두 가지 도구를 제공합니다:
search_drugs_by_name의약품 이름으로 대략적인 정보를 검색합니다.
파라미터:
drugname (string): 검색할 의약품의 이름 (영문 또는 한글)
반환값:
검색된 의약품 목록 (JSON 배열)
각 항목에는 약품명, 제조사, 효능, 용법용량 등의 기본 정보 포함
get_drug_detail_by_id의약품 코드로 상세 정보를 조회합니다.
파라미터:
drugcode (string): 의약품 코드 (search_drugs_by_name의 결과에서 획득)
반환값:
의약품의 상세 정보 (JSON 배열)
포함 정보: 성분, 첨가제, 보관방법, 주의사항, 임부/수유부 정보 등
Related MCP server: MedData MCP Server
pnpm installpnpm buildpnpm startpnpm devpnpm testClaude Desktop 또는 다른 MCP 클라이언트에서 이 서버를 사용하려면, 설정 파일에 다음을 추가하세요:
{
"mcpServers": {
"kpic": {
"command": "node",
"args": ["/path/to/kpic-mcp/dist/index.js"]
}
}
}kpic-mcp/
├── src/
│ ├── index.ts # MCP 서버 메인 엔트리포인트
│ ├── kpic-api.ts # KPIC API 클라이언트 함수
│ └── types.ts # TypeScript 타입 정의
├── __tests__/
│ └── kpic-api.test.ts # 테스트 코드
├── dist/ # 빌드 결과물 (TypeScript 컴파일 후)
├── package.json
├── tsconfig.json
└── README.md// 타이레놀 검색
search_drugs_by_name("타이레놀")// 특정 의약품 코드로 상세 정보 조회
get_drug_detail_by_id("2013062800004")Runtime: Node.js 18+
Language: TypeScript 5.x
Framework: MCP SDK (@modelcontextprotocol/sdk)
HTTP Client: Native Fetch API
Testing: Jest + ts-jest
Code Quality: ESLint, Prettier
Package Manager: pnpm
MIT
이 서버는 약학정보원의 공개 API를 사용합니다. API 사용 시 해당 사이트의 이용 약관을 준수해야 합니다.
약학정보원의 의약품 코드로 의약품의 상세정보를 가져옵니다. search_drugs_by_name()로 조회한 정보가 부족할 때 사용할 수 있습니다.
| Name | Required | Description | Default |
|---|---|---|---|
| drugcode | Yes | search_drugs_by_name()의 결과 값에 기재된 의약품의 drug_code 값 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates this is a read operation (fetching information) but doesn't specify authentication requirements, rate limits, error conditions, or what constitutes 'detailed information' beyond what search_drugs_by_name provides. The description adds some context about the data source but lacks comprehensive behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of just two sentences that are perfectly front-loaded and efficient. The first sentence establishes the core purpose, and the second provides crucial usage guidance. Every word earns its place with no redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter read tool with no annotations and no output schema, the description provides adequate purpose and usage guidance but lacks details about what 'detailed information' includes, error handling, or response format. The description compensates somewhat by linking to the sibling tool, but more behavioral context would be helpful given the absence of structured metadata.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the schema already fully documents the single parameter. The description adds valuable context by explaining the relationship between this parameter and the sibling tool: 'search_drugs_by_name()의 결과 값에 기재된 의약품의 drug_code 값' (drug_code value from search_drugs_by_name() results). This provides practical guidance on parameter sourcing beyond what the schema alone offers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('가져옵니다' - fetches/retrieves), resource ('의약품의 상세정보' - detailed drug information), and source ('약학정보원의 의약품 코드로' - using drug code from Pharmaceutical Information Service). It explicitly distinguishes from its sibling tool search_drugs_by_name by mentioning when this tool should be used instead.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool versus alternatives: 'search_drugs_by_name()로 조회한 정보가 부족할 때 사용할 수 있습니다' (can be used when information retrieved from search_drugs_by_name() is insufficient). This clearly establishes the relationship between the two tools and provides specific context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
약학정보원에서 의약품 이름으로 대략적인 정보들을 가져옵니다. 이름이 유사한 의약품 여러개가 나올 수 있습니다. 더 자세한 정보가 필요하다면 get_drug_detail_by_id()로 조회해야 합니다.
| Name | Required | Description | Default |
|---|---|---|---|
| drugname | Yes | 검색할 의약품의 이름 (영문 또는 한글) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It usefully adds that '이름이 유사한 의약품 여러개가 나올 수 있습니다' (multiple drugs with similar names may appear), which is important behavioral context about fuzzy matching. However, it doesn't disclose other behavioral traits like rate limits, authentication needs, error conditions, or what '대략적인 정보' (approximate information) specifically entails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with two sentences that each serve a clear purpose: the first states the tool's function, and the second provides important behavioral context and alternative guidance. It's front-loaded with the core purpose and wastes no words, though it could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter search tool with no annotations and no output schema, the description provides adequate but incomplete context. It covers the purpose, behavioral nuance about fuzzy matching, and alternative tool, but doesn't explain what information is returned or any limitations. Given the complexity is low (one parameter), it's minimally viable but could better address output expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'drugname' well-documented in the schema as '검색할 의약품의 이름 (영문 또는 한글)' (drug name to search, English or Korean). The description doesn't add any parameter-specific information beyond what the schema provides, so it meets the baseline of 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '약학정보원에서 의약품 이름으로 대략적인 정보들을 가져옵니다' (retrieves approximate drug information by name from the Pharmaceutical Information Center). It specifies the action (retrieve), resource (drug information), and source (Pharmaceutical Information Center). However, it doesn't explicitly differentiate from its sibling tool beyond mentioning it as an alternative for detailed information.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for usage: it's for approximate information retrieval by drug name, with the note that similar-named drugs may appear. It explicitly mentions the alternative tool 'get_drug_detail_by_id()' for detailed information, giving good guidance on when to use each. However, it doesn't specify when NOT to use this tool or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_drug_detail_by_idsearch_drugs_by_nameScored across 2 tools
The two tools have clearly distinct purposes: search_drugs_by_name retrieves preliminary information by drug name, while get_drug_detail_by_id fetches detailed information by drug code. Their descriptions explicitly reference each other to clarify when to use which, eliminating any ambiguity.
Both tools follow a consistent verb_noun pattern (search_drugs_by_name and get_drug_detail_by_id), using snake_case and descriptive names that clearly indicate their functions and parameters. There are no deviations in naming style.
With only 2 tools, the server feels under-scoped for a drug information domain. While the tools cover basic search and detail retrieval, typical drug information systems might include additional operations like filtering by category, checking interactions, or updating data, making this set appear thin and limited.
The tool set is severely incomplete for a drug information server. It lacks essential operations such as creating, updating, or deleting drug records, and does not cover common needs like drug interactions, dosage guidelines, or category-based searches. This will likely cause agent failures when more comprehensive tasks are required.
Look up Korean drug ingredient and product data by HIRA component and product codes via Pilldoc. V…
Search company disclosures and financial statements from the Korean market. Retrieve stock profile…
Drug-drug interaction checker for clinical LLMs using RxNorm and DailyMed.
Search and export FDA drug labels by brand name, generic ingredient, or UNII code.
