Git Code Review MCP
Enables AI assistants to perform code reviews by providing access to staged files, git diffs, and repository file content. It allows users to evaluate changes and context within any local git repository before committing or pushing.
README
Git Code Review MCP
An MCP (Model Context Protocol) server that allows AI to review your changes before pushing. This tool provides AI assistants with access to git repository information, staged files, and diffs to help with code review workflows.
Features
- Get Staged Files: List all files currently staged for commit
- View Diffs: Show the diff of staged changes with space-change filtering
- File Content Access: Retrieve the content of any file from the repository
- Repository Agnostic: Works with any git repository by specifying the path
Example MCP Client Configuration
If you're using this with an MCP client, add it to your configuration:
{
"mcpServers": {
"git-codereview": {
"command": "npx",
"args": ["git-codereview"]
}
}
}
Installation
The easiest way to use this MCP server is with npx:
npx git-codereview
This will run the MCP server directly without needing to install it globally.
Alternative Installation Methods
Global Installation
npm install -g git-codereview
git-codereview
Local Development
git clone https://github.com/AyoubTRD/git-codereview-mcp.git
cd git-codereview-mcp
npm install
npm run build
node build/index.js
Usage
This MCP server runs over stdio and is designed to be used with MCP-compatible AI tools. The server provides three main tools:
Available Tools
-
get_staged_files
- Lists all files currently staged for commit
- Requires:
repoPath(full path to git repository)
-
get_diff
- Shows the diff of staged files with added/modified filter
- Ignores whitespace changes for cleaner output
- Requires:
repoPath(full path to git repository)
-
get_file_content
- Retrieves the content of any file from the repository
- Useful when diff doesn't provide enough context
- Requires:
repoPath(full path to git repository) andfilePath(relative path to file)
Requirements
- Node.js (version 16 or higher)
- Git repository (the target repository must be git-initialized)
- MCP-compatible AI tool or client
License
ISC
Contributing
Issues and pull requests are welcome at GitHub.
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。