cs-ontology
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_conceptsA | 낱말로 개념을 찾는다. 결과는 개념 id, 제목, 중요도(별 1~5). 예: "인터럽트", "캐시". |
| get_conceptB | 개념 하나의 정의(왜 생겼나, 핵심, 계산 이유), 중요도, 출제 정보, 바로 앞 개념, 바로 열리는 개념을 돌려준다. |
| get_prerequisite_pathB | 개념 하나를 이해하는 데 필요한 모든 선행 개념을 깊이별로 돌려준다. L0이 출발점이다. |
| find_concepts_for_exam_itemsA | 교재 문제 번호("056"), 모의고사("모의1-22"), 공식 예시("예시06")를 받아 각 문제가 묻는 개념을 돌려준다. |
| rank_shared_prerequisitesB | 개념 여러 개가 공통으로 기대는 가장 구체적인 선행 개념을, 공유하는 개념 수가 많은 순서로 돌려준다. |
| diagnose_wrong_answersA | 틀린 문제 목록으로 진단한다. 처음엔 items만 넣으면 공통 선행 개념과 학생에게 물어볼 다음 질문(next_question)을 준다. 학생의 답을 known(설명 가능) / confused(헷갈림) / asked(넘어감 포함 이미 물어본 것)에 넣어 다시 부르면, next_question이 null이 될 때 plan(막힌 지점, 복습 순서)을 준다. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| ontology-schema | 클래스, 관계, 규모 |
TDQS
Scored across 6 tools
Each tool targets a distinct operation: search vs. single-concept retrieval, single-concept prerequisite path vs. multi-concept shared prerequisites, exam-item mapping vs. wrong-answer diagnosis. The prerequisite-related tools are separated by single vs. multiple concepts, and the diagnostic tool is clearly a workflow wrapper rather than a duplicate.
All names use snake_case and follow a verb_noun pattern (search_concepts, get_concept, get_prerequisite_path, find_concepts_for_exam_items, rank_shared_prerequisites, diagnose_wrong_answers). Verb choices vary appropriately by action while the convention remains predictable.
Six tools are well-scoped for a read-only concept-ontology/diagnostic server; each covers a distinct part of the workflow (search, inspect, prerequisite traversal, exam mapping, shared-prerequisite ranking, diagnosis). No tool appears redundant or missing at the count level.
The surface covers the core diagnostic workflow and concept/prerequisite/exam lookups, but there is no browse/list-all-concepts operation and no reverse dependency traversal (concepts that depend on a given concept). These are minor gaps an agent can often work around via search and get_concept.