Hi-AI
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_current_timeB | 지금 몇시|현재 시간|몇시야|what time|current time|time now - Get current time |
| preview_ui_asciiA | UI 만들어|페이지 개발|페이지 만들어|컴포넌트 작성|레이아웃|화면 구성|create page|build UI|design component|make page|develop page - Preview UI before coding |
| save_memoryA | 중요한 정보를 장기 메모리에 저장합니다. 프로젝트 결정사항, 아키텍처, 설정 등을 기록하세요. 키워드: 기억해, remember, 저장해, save, memorize, keep 💡 저장 후 link_memories로 관련 메모리를 연결하면 지식 그래프가 구축됩니다. |
| recall_memoryA | 특정 메모리를 키로 조회합니다. 키워드: 떠올려, recall, 기억나, remember what, what was, remind 💡 전체 컨텍스트가 필요하면 get_session_context를 먼저 사용하세요. |
| update_memoryC | 수정해|업데이트|바꿔|update|change|modify|edit - Update existing memory |
| delete_memoryA | 잊어|삭제해|지워|forget|delete|remove|erase - Delete specific memory |
| list_memoriesA | 저장된 메모리 목록을 조회합니다. 카테고리별 필터링 가능. 키워드: 뭐 있었지, 저장된 거, 목록, what did I save, list memories, show saved 💡 세션 시작 시 전체 컨텍스트가 필요하면 get_session_context를 사용하세요. |
| prioritize_memoryC | 중요한 거|우선순위|prioritize|important|what matters|priority - Prioritize memories by importance |
| link_memoriesB | 메모리 간 관계를 연결합니다 (지식 그래프). 키워드: 연결해, 관계 설정, 링크, connect memories, link, relate 사용 예시:
|
| get_memory_graphA | 메모리 지식 그래프를 조회합니다. 키워드: 그래프, 관계도, 연결 보기, memory graph, relations, connections 사용 예시:
|
| search_memories_advancedA | 고급 멀티 전략 메모리 검색을 수행합니다. 키워드: 고급 검색, 찾아, 스마트 검색, advanced search, find memories 검색 전략:
사용 예시:
|
| create_memory_timelineC | 메모리 타임라인을 생성합니다. 키워드: 타임라인, 시간순, 히스토리, timeline, history, chronological 사용 예시:
|
| get_session_contextA | 🚀 [새 대화/세션 시작 시 자동 실행 권장] 이전 세션의 메모리, 지식 그래프, 최근 작업 내역을 한 번에 조회합니다. 이 도구는 새로운 대화를 시작할 때 가장 먼저 실행하면 좋습니다. 프로젝트의 컨텍스트를 빠르게 파악할 수 있습니다. 키워드: 세션 시작, 컨텍스트, 이전 작업, session start, context, previous work, what did we do 사용 예시:
|
| find_symbolC | 함수 찾아|클래스 어디|변수 위치|find function|where is|locate - Find symbol definitions |
| find_referencesC | 어디서 쓰|참조|사용처|find usage|references|where used - Find symbol references |
| analyze_dependency_graphB | 코드 의존성 그래프를 분석합니다. 키워드: 의존성, 관계 분석, 순환 참조, dependency graph, circular dependency 분석 내용:
사용 예시:
|
| get_coding_guideB | 가이드|규칙|컨벤션|guide|rules|convention|standards|best practices - Get coding guide |
| apply_quality_rulesC | 규칙 적용|표준 적용|apply rules|apply standards|follow conventions|적용해 - Apply quality rules |
| validate_code_qualityC | 품질|리뷰|검사|quality|review code|check quality|validate|코드 리뷰 - Validate code quality |
| analyze_complexityC | 복잡도|복잡한지|complexity|how complex|난이도 - Analyze code complexity |
| check_coupling_cohesionC | 결합도|응집도|coupling|cohesion|dependencies check|module structure - Check coupling and cohesion |
| suggest_improvementsC | 개선|더 좋게|리팩토링|improve|make better|refactor|optimize|enhance code - Suggest improvements |
| create_thinking_chainC | 생각 과정|사고 흐름|연쇄적으로|thinking process|chain of thought|reasoning chain - Create sequential thinking chain |
| analyze_problemC | 문제 분석|어떻게 접근|분석해줘|analyze this|how to approach|break this down - Break down complex problem into structured steps |
| step_by_step_analysisC | 단계별|차근차근|하나씩|step by step|one by one|gradually - Perform detailed step-by-step analysis |
| format_as_planC | 계획으로|정리해줘|체크리스트|format as plan|make a plan|organize this|checklist - Format content into clear plans |
| generate_prdB | PRD|요구사항 문서|제품 요구사항|product requirements|requirements document|spec document - Generate Product Requirements Document |
| create_user_storiesB | 스토리|사용자 스토리|user story|user stories|as a user - Generate user stories from requirements |
| analyze_requirementsC | 요구사항 분석|필요한 것들|requirements analysis|what we need|analyze requirements|필수 기능 - Analyze project requirements |
| feature_roadmapC | 로드맵|일정|계획표|roadmap|timeline|project plan|development schedule - Generate development roadmap |
| enhance_promptB | 구체적으로|자세히|명확하게|더 구체적으로|be specific|more detail|clarify|elaborate|vague - Transform vague requests |
| analyze_promptC | 프롬프트 분석|평가|점수|얼마나 좋은지|analyze prompt|rate this|score|how good|prompt quality - Analyze prompt quality |
| enhance_prompt_geminiA | 프롬프트 개선|제미나이 전략|품질 향상|prompt enhancement|gemini strategies|quality improvement - Enhance prompts using Gemini API prompting strategies (Few-Shot, Output Format, Context) |
| apply_reasoning_frameworkB | 추론 프레임워크|체계적 분석|논리적 사고|reasoning framework|systematic analysis|logical thinking - Apply 9-step reasoning framework to analyze complex problems systematically |
| get_usage_analyticsB | 도구 사용 분석 및 통계를 조회합니다. 키워드: 분석, 통계, 사용량, analytics, statistics, usage 제공 정보:
사용 예시:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| code-review | Comprehensive code review with quality analysis |
| problem-solver | Step-by-step problem analysis and solution planning |
| project-kickoff | Start a new project with PRD, user stories, and roadmap |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| 🧠 Session Context (Auto-load) | 세션 시작 시 이전 메모리와 지식 그래프 컨텍스트를 자동으로 제공합니다. 새 대화를 시작할 때 이 리소스를 읽으면 프로젝트 컨텍스트를 빠르게 파악할 수 있습니다. |
| Code Quality Rules | Best practices and quality rules for code development |
| Naming Conventions | Naming conventions for variables, functions, and components |
| Hi-AI Capabilities | Overview of Hi-AI tools and features |
TDQS
Scored across 35 tools
Multiple tools have overlapping purposes, causing significant ambiguity. For example, analyze_complexity, analyze_dependency_graph, check_coupling_cohesion, and validate_code_quality all relate to code analysis with unclear boundaries. Similarly, analyze_prompt, enhance_prompt, and enhance_prompt_gemini overlap in prompt improvement, while create_thinking_chain, apply_reasoning_framework, and step_by_step_analysis all involve structured problem-solving. This overlap makes it difficult for an agent to reliably select the correct tool.
Most tools follow a consistent verb_noun pattern (e.g., analyze_complexity, create_memory_timeline, get_current_time), which aids predictability. However, there are minor deviations like preview_ui_ascii (verb_noun_adjective) and feature_roadmap (noun_noun), slightly disrupting the pattern. Overall, the naming is largely consistent and readable.
With 35 tools, the count is excessive for the server's apparent scope of AI-assisted coding and memory management. This high number suggests redundancy and fragmentation, as seen in overlapping analysis and prompt tools, making the set feel heavy and unwieldy. A more focused set of 10-20 tools would better serve the domain without overwhelming agents.
The tool surface covers core areas like code analysis, memory management, and project planning with good CRUD coverage for memories (save, list, recall, update, delete, link). Minor gaps exist, such as no explicit tool for deleting or updating code analysis results, but agents can work around these using existing tools like update_memory or validate_code_quality. Overall, the set supports key workflows without major dead ends.