返回 MCP 目录
public公开dns本地运行

Git 仓库解析器

帮助AI读取GitHub仓库结构和重要文件。想快速了解一个仓库是关于什么的吗?用“read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works”来提示它,即可确定代码在技术上是如何工作的。

article

README

MCP Git Ingest

smithery badge

A Model Context Protocol (MCP) server that helps read GitHub repository structure and important files.

Inspired by gitingest.

Configuration

{
    "mcpServers": {
        "mcp-git-ingest": {
            "command": "uvx",
            "args": ["--from", "git+https://github.com/adhikasp/mcp-git-ingest", "mcp-git-ingest"],
        }
    }
}

Usage

Using mcp-client-cli:

$ llm read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works

I'll help you understand the technical details of the mcp-git-ingest repository. I'll first fetch the directory structure and then read the important files to analyze how the code works.

Tool Calls:
  github_directory_structure
  Args:
    repo_url: https://github.com/adhikasp/mcp-git-ingest

Now, I'll read the important files to understand the technical implementation:

Tool Calls:
  github_read_important_files
  Args:
    repo_url: https://github.com/adhikasp/mcp-git-ingest
    file_paths: ['README.md', 'src/mcp_git_ingest/main.py', 'pyproject.toml']

Let me break down how this code technically works:

1. Purpose:
The `mcp-git-ingest` is a Model Context Protocol (MCP) server designed to help read GitHub repository structures and important files. It provides two main tools:
- `github_directory_structure`: Returns a tree-like representation of a repository's directory structure
- `github_read_important_files`: Reads and returns the contents of specified files in a repository

2. Technical Implementation:

a. Dependencies:
- Uses `fastmcp` for creating an MCP server
- Uses `gitpython` for Git repository operations
- Requires Python 3.8+

b. Key Functions:

`clone_repo(repo_url: str) -> str`:
- Creates a deterministic temporary directory based on the repository URL's hash
- Checks if the repository is already cloned
- If not, clones the repository
- Handles error cases and cleanup
- Returns the path to the cloned repository

`get_directory_tree(path: str, prefix: str = "") -> str`:
- Recursively generates a tree-like directory structure
- Skips `.git` directories
- Uses Unicode box-drawing characters to create a visual tree representation
- Handles sorting of entries

`github_directory_structure(repo_url: str) -> str`:
- Clones the repository
- Generates directory tree
- Cleans up the temporary repository after processing
- Returns the tree structure or an error message

`github_read_important_files(repo_url: str, file_paths: List[str]) -> dict[str, str]`:
- Clones the repository
- Reads specified files
- Returns a dictionary mapping file paths to their contents
- Handles file reading errors
- Cleans up the temporary repository

3. Error Handling:
- Uses try-except blocks to handle repository cloning, file reading errors
- Ensures temporary directories are always cleaned up using `finally` blocks
- Returns descriptive error messages

4. Performance Optimizations:
- Uses a hash-based temporary directory naming to potentially reuse cloned repositories
- Checks for existing repositories before cloning
- Implements cleanup to prevent accumulation of temporary files

5. Unique Features:
- Deterministic temporary directory creation
- Unicode tree representation
- Flexible file reading with error handling

6. Execution:
- Can be run as a CLI tool via `mcp-git-ingest`
- Configured through `pyproject.toml`
- Depends on `fastmcp` for MCP server functionality

The code is a robust, flexible tool for programmatically exploring and reading GitHub repositories, with a focus on error handling and clean implementation.

Would you like me to elaborate on any specific aspect of the implementation?
help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端