디렉터리 구조를 시각화하고 분석하는 강력한 모델 컨텍스트 프로토콜(MCP) 구현. 이제 AI 어시스턴트가 프로젝트 구조를 효율적으로 이해하고 탐색하여 더욱 스마트한 코드 탐색 및 프로젝트 구성 통찰력을 제공할 수 있습니다.
다음으로 구성됨:
심층 디렉토리 트리 시각화
구성 가능한 깊이 기반 트리 생성
스마트 패턴 기반 파일/디렉토리 제외
깔끔하고 읽기 쉬운 트리 출력 형식
실시간 디렉토리 구조 업데이트
타겟 디렉토리 분석
데모:
Related MCP server: MCP Filesystem Server
Node.js (v18 이상)
시작하는 가장 쉬운 방법은 Smithery를 사용하는 것입니다.
지엑스피1
커서 설정 열기 → MCP → 새 MCP 서버 추가
다음 설정으로 구성하세요.
{
"deep-directory-tree": {
"command": "npx",
"args": ["-y", "@andredezzy/deep-directory-tree-mcp"]
}
}MCP 구성에 다음을 추가하세요.
{
"mcpServers": {
"deep-directory-tree": {
"command": "npx",
"args": ["-y", "@andredezzy/deep-directory-tree-mcp"]
}
}
}AI 도우미를 위한 일반적인 명령:
"디렉토리 구조를 보여주세요"
"프로젝트 트리를 최대 4단계까지 시각화"
"테스트 디렉토리를 제외한 파일 표시"
Bun 런타임 (필수)
# Clone the repository
git clone https://github.com/andredezzy/deep-directory-tree-mcp.git
cd deep-directory-tree-mcp
# Install dependencies
bun install
# Build the project
bun run build커서 설정 열기 → MCP → 새 MCP 서버 추가
다음 설정으로 구성하세요.
{
"deep-directory-tree": {
"command": "node",
"args": ["ABSOLUTE_PATH_TO_MCP_SERVER/bin/deep-directory-tree.js"]
}
}MCP 구성에 다음을 추가하세요.
{
"mcpServers": {
"deep-directory-tree": {
"command": "node",
"args": ["ABSOLUTE_PATH_TO_MCP_SERVER/bin/deep-directory-tree.js"]
}
}
}저장소를 포크하세요
기능 브랜치 생성( git checkout -b feature/amazing-feature )
변경 사항 커밋( git commit -m 'Add feature' )
브랜치에 푸시( git push origin feature/amazing-feature )
풀 리퀘스트 열기
도움이 필요하신가요? 다음 자료를 참고해 보세요.
MIT 라이센스 - 자세한 내용은 라이센스 파일을 참조하세요.
Get deep directory tree
| Name | Required | Description | Default |
|---|---|---|---|
| options | No | Tree generation options | |
| path | Yes | Path to get the directory tree (preferably absolute path) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states the action without detailing output format, performance implications, error handling, or system impacts. This is inadequate for a tool that likely returns structured data and may have depth/exclusion constraints.
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 extremely concise with a single phrase, front-loaded and without unnecessary words. It efficiently conveys the core intent, though this brevity contributes to gaps in other dimensions.
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?
Given no annotations, no output schema, and a tool with behavioral complexity (e.g., tree generation with exclusions), the description is incomplete. It fails to explain return values, error cases, or practical use, leaving significant gaps for agent understanding.
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?
Schema description coverage is 100%, so the schema fully documents parameters like 'path' and 'options' with defaults. The description adds no parameter semantics beyond what the schema provides, meeting the baseline for high coverage but not enhancing understanding.
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 'Get deep directory tree' states the basic action (get) and resource (directory tree), but lacks specificity about what 'deep' means or how it differs from a shallow tree. Without sibling tools, differentiation isn't needed, but the purpose remains vague about the nature of the operation beyond the literal interpretation.
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?
No guidance is provided on when to use this tool versus alternatives or any prerequisites. The description does not mention context like file system exploration or debugging scenarios, leaving the agent with no usage cues beyond the tool name.
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.
v1.0.0get_deep_directory_treeScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly distinct by default.
A single tool inherently follows a consistent naming pattern, as there are no other tools to compare against. The name 'get_deep_directory_tree' uses a clear verb_noun structure.
One tool is too few for a server named 'deep-directory-tree-mcp', which suggests a scope that might include operations like listing, filtering, or modifying directory trees. A single get operation feels thin and incomplete for this domain.
The tool surface is severely incomplete for a directory tree domain. It only provides a get operation, with obvious gaps such as creating, updating, deleting, or searching directory trees, which are essential for basic CRUD coverage.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Code-map tools for AI agents: see a repo's structure first, then edit only what matters.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
