pia-mcp-server-git: A git MCP server

Overview

A Model Context Protocol server for Git repository interaction and automation. This server provides tools to read, search, and manipulate Git repositories via Large Language Models.

Requires MCP Python SDK 1.x (mcp>=1.29.0,<2). SDK 2.0 renamed APIs this server uses. The port to v2 is in progress.

Please note that pia-mcp-server-git is currently in early development. The functionality and available tools are subject to change and expansion as we continue to develop and improve the server.

Tools

1. git_status

   • Shows the working tree status
   • Input:
     • repo_path (string): Path to Git repository
   • Returns: Current status of working directory as text output

2. git_diff_unstaged

   • Shows changes in working directory not yet staged
   • Inputs:
     • repo_path (string): Path to Git repository
     • context_lines (number, optional): Number of context lines to show (default: 3)
   • Returns: Diff output of unstaged changes

3. git_diff_staged

   • Shows changes that are staged for commit
   • Inputs:
     • repo_path (string): Path to Git repository
     • context_lines (number, optional): Number of context lines to show (default: 3)
   • Returns: Diff output of staged changes

4. git_diff

   • Shows differences between branches or commits
   • Inputs:
     • repo_path (string): Path to Git repository
     • target (string): Target branch or commit to compare with
     • context_lines (number, optional): Number of context lines to show (default: 3)
   • Returns: Diff output comparing current state with target

5. git_commit

   • Records changes to the repository
   • Inputs:
     • repo_path (string): Path to Git repository
     • message (string): Commit message
   • Returns: Confirmation with new commit hash

6. git_add

   • Adds file contents to the staging area
   • Inputs:
     • repo_path (string): Path to Git repository
     • files (string[]): Array of file paths to stage
   • Returns: Confirmation of staged files

7. git_reset

   • Unstages all staged changes
   • Input:
     • repo_path (string): Path to Git repository
   • Returns: Confirmation of reset operation

8. git_log

   • Shows the commit logs with optional date filtering
   • Inputs:
     • repo_path (string): Path to Git repository
     • max_count (number, optional): Maximum number of commits to show (default: 10)
     • start_timestamp (string, optional): Start timestamp for filtering commits. Accepts ISO 8601 format (e.g., '2024-01-15T14:30:25'), relative dates (e.g., '2 weeks ago', 'yesterday'), or absolute dates (e.g., '2024-01-15', 'Jan 15 2024')
     • end_timestamp (string, optional): End timestamp for filtering commits. Accepts ISO 8601 format (e.g., '2024-01-15T14:30:25'), relative dates (e.g., '2 weeks ago', 'yesterday'), or absolute dates (e.g., '2024-01-15', 'Jan 15 2024')
   • Returns: Array of commit entries with hash, author, date, and message

9. git_create_branch

   • Creates a new branch
   • Inputs:
     • repo_path (string): Path to Git repository
     • branch_name (string): Name of the new branch
     • base_branch (string, optional): Base branch to create from (defaults to current branch)
   • Returns: Confirmation of branch creation

10. git_checkout

    • Switches branches
    • Inputs:
      • repo_path (string): Path to Git repository
      • branch_name (string): Name of branch to checkout
    • Returns: Confirmation of branch switch

11. git_show

    • Shows the contents of a commit
    • Inputs:
      • repo_path (string): Path to Git repository
      • revision (string): The revision (commit hash, branch name, tag) to show
    • Returns: Contents of the specified commit

12. git_branch

    • List Git branches
    • Inputs:
      • repo_path (string): Path to the Git repository.
      • branch_type (string): Whether to list local branches ('local'), remote branches ('remote') or all branches('all').
      • contains (string, optional): The commit sha that branch should contain. Do not pass anything to this param if no commit sha is specified
      • not_contains (string, optional): The commit sha that branch should NOT contain. Do not pass anything to this param if no commit sha is specified
    • Returns: List of branches

Installation

Using uv (recommended)

Install uv, then prepare the project environment from the lock file:

uv --directory /path/to/pia-mcp-server-git sync --locked

Using pip

Alternatively, install the package with pip:

pip install pia-mcp-server-git

Deployment

This server communicates over stdio. A host service must launch the process and connect its standard input and output to the MCP client. The project does not expose an HTTP endpoint by itself.

Using uv from the source tree

uv --directory /path/to/pia-mcp-server-git run --no-sync pia-mcp-server-git --repository /path/to/git/repo

--repository limits the server to the specified repository and its subdirectories. Omit --no-sync if the environment has not been prepared with uv sync.

Using an installed package

pia-mcp-server-git --repository /path/to/git/repo

The equivalent module invocation is:

python -m mcp_server_git --repository /path/to/git/repo

Verification

Use the MCP Inspector to verify the stdio server locally:

npx @modelcontextprotocol/inspector uv --directory /path/to/pia-mcp-server-git run --no-sync pia-mcp-server-git --repository /path/to/git/repo

For automated unit tests:

uv --directory /path/to/pia-mcp-server-git run pytest

发布到 PyPI

发布脚本使用 PyPI 项目级 API Token 进行身份认证，并通过 Windows DPAPI 将凭据加密保存在本地。该流程仅适用于 Windows PowerShell 环境。

发布前准备

• 安装并确保 uv 命令可用。
• 在 PyPI 中创建仅限 pia-mcp-server-git 项目的 API Token。
• 确认 pyproject.toml 中的 version 尚未发布。PyPI 不允许覆盖已经发布的同版本文件。

1. 配置 PyPI 凭据

在项目根目录运行：

.\scripts\setup-pypi-auth.ps1

根据提示输入 PyPI 项目级 API Token。脚本会将加密凭据保存到：

.secrets/pypi-token.clixml

不要手动把明文 Token 写入该文件，也不要提交或分享 .secrets 目录。凭据通常只能由创建它的同一台 Windows 计算机和同一 Windows 用户解密。除非 Token 发生变化或被撤销，否则不需要在每次发布前重复配置。

2. 发布包

确认版本号和待发布内容无误后运行：

.\scripts\publish-pypi.ps1

发布脚本会依次执行以下操作：

1. 从 Windows 凭据文件中临时读取 PyPI Token。
2. 使用 uv build 构建 wheel 和源码分发包。
3. 使用 uv publish --dry-run 验证发布参数和制品。
4. 将两个制品正式上传到 PyPI。
5. 清理临时 Token 和临时构建目录。

终端显示以下内容表示发布成功：

PyPI publish completed successfully.

发布完成后，可以在以下页面检查版本和制品：

https://pypi.org/project/pia-mcp-server-git/

常见问题

• No encrypted PyPI credential file was found：先运行 setup-pypi-auth.ps1 配置凭据。
• File already exists：当前版本已经发布，需要先在 pyproject.toml 中更新版本号，再重新构建和发布。
• Token 无效或已撤销：在 PyPI 创建新的项目级 Token，然后重新运行凭据配置脚本。