git-quick-stats MCP server
Exposes git-quick-stats commands as MCP tools to analyze git repositories via natural language.
README
MCP Server for git-quick-stats
This folder contains a small MCP server that exposes git-quick-stats commands as MCP tools.
Setup
Install uv first (one-time):
curl -LsSf https://astral.sh/uv/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"
cd mcp-server
uv venv .venv
uv sync --dev
Or using Make:
make install
This installs:
- Runtime dependencies from
pyproject.toml - Development tools (including Black) from the
devdependency group
Run
uv run -m src.server
The server uses stdio transport, so configure your MCP client to launch this command.
On first tool execution, the server automatically downloads git-quick-stats
into .mcp-tools/git-quick-stats inside this project if the script is not
already present at project root.
To pin a specific upstream branch/tag/commit for downloads, set:
export GIT_QUICK_STATS_REF=<ref>
Example MCP Client Config
{
"mcpServers": {
"git-quick-stats": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/git-quick-stats/mcp-server",
"-m",
"src.server"
]
}
}
}
VS Code Config
Add one of the following entries to your VS Code MCP settings depending on your OS.
Windows (native Python/uv)
{
"mcpServers": {
"git-quick-stats": {
"command": "uv",
"args": [
"run",
"--directory",
"C:\\absolute\\path\\to\\git-quick-stats\\mcp-server",
"-m",
"src.server"
]
}
}
}
Windows (WSL Ubuntu)
{
"mcpServers": {
"git-quick-stats": {
"command": "wsl.exe",
"args": [
"-d",
"Ubuntu",
"uv",
"run",
"--directory",
"/home/your-user/projects/git-quick-stats/mcp-server",
"-m",
"src.server"
]
}
}
}
Linux
{
"mcpServers": {
"git-quick-stats": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/git-quick-stats/mcp-server",
"-m",
"src.server"
]
}
}
}
macOS
{
"mcpServers": {
"git-quick-stats": {
"command": "uv",
"args": [
"run",
"--directory",
"/Users/your-user/path/to/git-quick-stats/mcp-server",
"-m",
"src.server"
]
}
}
}
Make Targets
make help
make bootstrap-uv
make install
make run
make format
make format-check
Docker Compose
Run the MCP server with Docker Compose:
docker compose up --build
Or via Make:
make docker-up
make docker-logs
make docker-down
Usage Notes
- Set
repo_pathto the git repository you want to inspect. - Some options need extra values, which should be passed using tool arguments:
authorfor options that need_GIT_AUTHORbranchfor options that need_GIT_BRANCHtagfor options that need_GIT_TAG
- The
--new-contributorsoption prompts for a date in the shell script. Usestdin_inputwith one date line, for example:2025-01-01\n.
AI Output Example
Example tool call from an AI assistant:
{
"tool": "run_git_quick_stats",
"arguments": {
"option": "--new-contributors",
"repo_path": "/absolute/path/to/git-quick-stats",
"stdin_input": "2025-01-01\n"
}
}
Example tool result:
{
"ok": true,
"exit_code": 0,
"stdout": "New contributors since 2025-01-01:\\n\\n 1 example.user@example.com\\n...",
"stderr": ""
}
Example AI response to user:
New contributors report generated successfully using stdin date input (2025-01-01). I can also run the same report for another date range if you want.
推荐服务器
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。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。