nl-openapi-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NL_API_KEY | Yes | Your National Library of Korea OpenAPI key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| nl_statusA | 연결 점검 — 인증키 보유 여부 + 소장자료 검색 API 실제 왕복 1회. |
| nl_searchA | [소장자료 검색] 국립중앙도서관 소장자료를 검색한다. kwd: 검색어.
exact: True 면 큰따옴표 구문검색(토큰 인접 요구). 특정 자료를 정확히 찾을 때만 쓸 것 —
코퍼스 수집에는 부적합하다(아래 참조).
srch_target: 실측 지원값 — ⚠️ 기본 검색은 제목 부분일치가 아니라 토큰 매칭 + 적합도 정렬이다.
⚠️ |
| nl_collectA | [수집] 검색어들을 각각 조회해 합집합으로 모으고 파일로 저장한다. terms: 변형어 목록(각각 개별 검색 후 합집합). 검색어를 쪼갤수록 500건 상한을 덜 받으므로
넓은 말 하나보다 좁은 말 여럿이 회수량이 많다.
kwd: 단일 검색어(terms 대신).
exact: 🔴 코퍼스 수집에는 쓰지 말 것. 구문검색은 토큰 인접을 요구해 한국어 복합어가
조사·수식어로 갈라진 표제( ⚠️ ⚠️ |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct purpose: nl_status verifies connectivity, nl_search performs a single query, and nl_collect aggregates multiple searches with saving and partitioning. Though nl_search and nl_collect both search, their roles are clearly separated (single vs. batch), so an agent cannot confuse them.
All tool names share the consistent 'nl_' prefix and lowercase_snake_case format. While 'status' is a noun and 'search'/'collect' are verbs, the naming is predictable and each name directly reflects its function, making the pattern easy to infer.
Three tools is a well-scoped count for a library search MCP, providing essential operations without redundancy. Each tool carries substantial functionality, especially nl_collect which bundles complex features like recursive partitioning and filtering, so every tool earns its place.
The set covers the full lifecycle of searching and collecting library records: health check, individual search, and batch collection with export options. It also addresses API limitations (e.g., 500-record cap) through built-in partitioning and provides explicit workarounds, leaving no obvious gaps for the stated domain.