MCP Git Ingest
Reads the structure and important files of a GitHub repository.
MCP Git Ingest
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?
Related Servers
GitHub MCP Server
Integrates with GitHub APIs for advanced automation and interaction, supporting both remote and local deployments.
GitHub Project Manager with Resource System
A server for GitHub project management with advanced resource management, capacity planning, and workload optimization capabilities.
Feather Code
A lightweight MCP server for interacting with GitHub repositories, requiring authentication.
GitHub Kanban MCP Server
Manage GitHub issues as a Kanban board using the gh CLI.
Git TS MCP
Execute Git commands safely through AI assistants like Claude.
GitHub Projects V2
Manage GitHub Projects V2 using the GitHub GraphQL API.
GitLab
Integrates with the GitLab REST API to manage repositories, issues, and merge requests.
GitHub Repository Manager
An MCP server that allows AI assistants to create and delete GitHub repositories. Requires a GITHUB_TOKEN for authentication.
GitLab Kanban
A server for managing GitLab Kanban board operations.
GitViz
Visualize Git history and commit logs with animations, making Git operations intuitive and easy to understand.