MCP Git Analysis Server

Provides commit, contributor, and file-change insights by analyzing local git repositories.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jaz-spec-alex_mcp_workshop": {
      "command": "python3",
      "args": [
        "/path/to/server.py"
      ]
    }
  }
}

This MCP server analyzes local git repositories to reveal insights about commits, contributors, and file changes. You can use it to understand project activity, identify hot spots in your codebase, and get a clear view of who contributed what over time. It exposes practical tools you can invoke from an MCP client to fetch structured analytics from your repositories.

How to use

You use this MCP server by configuring it as a local (stdio) MCP endpoint and then calling its available tools from your MCP client. The server runs as a local process and reads your git repositories to return analytic results such as commit statistics, hot spots, and contributor data. You can start by launching the server with the runtime command shown in the configuration snippet, then issue tool calls by name from your MCP client.

How to install

Prerequisites you need before installation are Python 3.8 or newer and Git installed on your system. You also need GitPython installed as a Python package.

Install project dependencies with the following command:

pip install -r requirements.txt

Prepare to run the server. You will launch the server process using Python against the server script that provides the MCP endpoint.

Option A: run directly with MCP Inspector (for development and testing):

mcp dev server.py

Option B: expose the server as an MCP stdio endpoint via a Python command (used by MCP clients):

python3 /path/to/server.py

Option C: configure a client to use the stdio server (example configuration shown in the next code block). Ensure the command and arguments are provided exactly as shown.

Configuration for MCP client usage

If you want to connect your MCP client to this server as a local process, provide the following stdio configuration. This runs the server via Python and points to the server script you are hosting locally.

{
  "mcpServers": {
    "git_analysis": {
      "command": "python3",
      "args": ["/path/to/server.py"]
    }
  }
}

Available tools

analyze_commits

Fetch commit statistics with optional filters such as count, author, or date range, returning detailed information about commits and their changes.

find_hot_spots

Identify the most frequently changed files, showing the number of commits per file and the count of unique authors.

get_contributors

List all contributors with statistics including commit counts, insertions, deletions, and the dates of their first and last commits.