Sponsored by Deepsite.site

MCP Git Ingest

Created By
adhikaspa year ago
A Model Context Protocol (MCP) server that helps read GitHub repository structure and important files.
Content

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?
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
WindsurfThe new purpose-built IDE to harness magic
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Amap Maps高德地图官方 MCP Server
Tavily Mcp
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
ChatWiseThe second fastest AI chatbot™
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
CursorThe AI Code Editor
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Serper MCP ServerA Serper MCP Server
DeepChatYour AI Partner on Desktop
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.