这是一个在指定目录下生成文件树的 MCP 服务器。根据以 开头的目录排除特定的文件或目录.或.gitignore中列出的条件。与 Claude 集成可以让 Claude 快速查看项目结构并帮助他确定要编辑的文件。
以 JSON 格式获取指定目录下的文件树。
根据.gitignore条件排除文件/目录
将目录结构表示为分层 JSON
Related MCP server: MCP Git Explorer
Python 3.10 或更高版本
紫外线
# uvのインストール
$ curl -LsSf https://astral.sh/uv/install.sh | sh
$ cd /path/to/mcp-src-tree
# ライブラリのインストール
$ uv sync将以下内容添加到claude_desktop_config.json ：
{
"mcpServers": {
"src-tree": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-src-tree", # このプロジェクトディレクトリの絶対パスに書き換えてください
"run",
"tree.py"
]
}
}
}请指定 src 上一级的根目录。当考虑.gitignore时，假定.gitignore直接存在于根目录下。 /Users/xxx/GitHub/xxx/ のソースツリーを確認してください，它将会起作用。
其回应如下：
はい、ソースツリーを確認させていただきます。
プロジェクトの構造を確認しました。以下のような構成になっています：
src/
└── xxxx/
├── __init__.py
├── converter.py
├── html_converter.py
├── image_processor.py
├── toc_analyzer.py
└── utils.py这使得 Claude 能够快速了解项目结构。
以 开头的目录.将被自动排除。与.gitignore中的模式匹配的文件和目录将自动从树中排除。例如，以下.gitignore配置是有效的：
__pycache__/
node_modules/
*.logGenerate a file tree for the specified directory, filtering files based on .gitignore. Traverses the filesystem and generates a JSON-formatted tree structure that preserves hierarchy.
Inputs: directory (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'get_src_tree' follows a clear verb_noun pattern.
A single tool is too few for most practical server purposes, as it severely limits functionality and flexibility. This server appears to offer only basic directory tree generation, which feels thin and under-scoped.
The server's domain seems to be file system or source tree operations, but with only one tool for generating a tree, there are significant gaps. Missing operations might include filtering by other criteria, updating trees, or handling file contents, making the surface incomplete for typical agent workflows.
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
Compare two JSON files deeply, ignoring order, to surface every difference. Get a clear, structure…
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
