What does this server do vs using git directly?
It wraps Git operations into MCP tools that LLMs can call programmatically, allowing automated repository interaction without manual command-line input.

@modelcontextprotocol
基本情報
Model Context Protocol Servers
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"git": {
"command": "uvx",
"args": [
"mcp-server-git",
"--repository",
"path/to/git/repo"
]
}
}
}`repo_path` (string): Path to Git repository
Current status of working directory as text output
`repo_path` (string): Path to Git repository
Diff output of unstaged changes
`repo_path` (string): Path to Git repository
Diff output of staged changes
`repo_path` (string): Path to Git repository
Diff output comparing current state with target
`repo_path` (string): Path to Git repository
Confirmation with new commit hash
`repo_path` (string): Path to Git repository
Confirmation of staged files
`repo_path` (string): Path to Git repository
Confirmation of reset operation
`repo_path` (string): Path to Git repository
Array of commit entries with hash, author, date, and message
`repo_path` (string): Path to Git repository
Confirmation of branch creation
`repo_path` (string): Path to Git repository
Confirmation of branch switch
`repo_path` (string): Path to Git repository
Contents of the specified commit
`repo_path` (string): Path to the Git repository.
List of branches
A Model Context Protocol (MCP) server that provides tools for LLMs to read, search, and manipulate Git repositories. It enables automated repository interaction and version control operations through a standard MCP interface.
Install with uvx mcp-server-git (no explicit install needed) or via pip install mcp-server-git. Add the server configuration to your MCP client (Claude Desktop, VS Code, Zed, or Zencoder) specifying the repository path with --repository. Run directly with python -m mcp_server_git if installed via pip.
git_statusgit_add and git_commitgit_create_branch and git_checkoutgit_branchIt wraps Git operations into MCP tools that LLMs can call programmatically, allowing automated repository interaction without manual command-line input.
Python and either `uv` (recommended) or pip. For Docker usage, Docker must be installed, and directories are mounted as bind mounts for repository access.
Use `uvx mcp-server-git` (no explicit install) or `pip install mcp-server-git`. For Docker, build with `docker build -t mcp/git .` from the source directory.
Run the MCP inspector: `npx @modelcontextprotocol/inspector uvx mcp-server-git`. Or check Claude logs with `tail -f ~/Library/Logs/Claude/mcp*.log`.
The server is currently in early development; tools and functionality are subject to change and expansion.
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
MCP server for Atlassian tools (Confluence, Jira)
A Git MCP server for AI agents. STDIO & Streamable HTTP.
MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version
MCP server that enables AI assistants to interact with Linear project management system through natural language, allowing users to retrieve, create, and update issues, projects, and teams.
コメント