MCP Git 安装

一个模型上下文协议（MCP）服务器，帮助读取GitHub存储库结构和重要文件。

灵感来自 吉廷斯特.

配置

JSON``` 1 2 3 4 5 6 7 8{ “mcpServers”: { “mcp-git-ingest”: { “command”: “uvx”, “args”: [“—from”, “git+https://github.com/adhikasp/mcp-git-ingest”, “mcp-git-ingest”], } } }

## 用法


使用 [mcp客户端cli](https://github.com/adhikasp/mcp-client-cli):

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63$ 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?