mcp-server-git
A Model Context Protocol server providing tools to read, search, and manipulate Git repositories programmatically via LLMs
Decision gist · record as of 2026-08-14
Yes, if you are building LLM-integrated development tools or AI assistants that need programmatic Git access. The package is actively maintained, has low install friction, and carries no security vulnerabilities. The MIT license poses no restrictions. The main caveat is that it is explicitly in early development—expect the tool set and behavior to evolve, and validate LLM-generated Git commands before execution in production repositories.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Git must be installed on the system.
- The server is designed to run as a background process managed by an MCP client (Claude Desktop, VS Code, Zed, etc.), not as a standalone library in your own Python code.
License · maintenance · safety
MIT (permissive) — MIT license is permissive—you can use, modify, and distribute this package freely with minimal restrictions, making it suitable for both open-source and commercial projects.
last release 2026-07-10 (35 days) · last repo commit 2026-08-10 · 89,561 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 774,459 downloads/mo, #5,094 on PyPI
Alternatives
Verify before relying
pip install mcp-server-git
# Run as a server (typically configured in Claude Desktop, VS Code, or Zed)
python -m mcp_server_git --repository /path/to/repo
# Or via uvx (recommended)
uvx mcp-server-git --repository /path/to/repo- Whether the package handles large repositories efficiently or has known performance limits.
- Whether all Git operations (especially git_commit, git_add, git_reset) are safe to invoke from untrusted LLM outputs without additional validation.
- Stability guarantees beyond 'early development' status—what breaking changes are expected.
What it is and what it does
mcp-server-git is a Model Context Protocol server that bridges Git repositories and Large Language Models. It exposes a set of Git operations—status, diff, commit, branch management, log queries, and more—as callable tools that an LLM can invoke to read and modify repositories. The server runs as a separate process and communicates with LLM clients (Claude Desktop, VS Code, Zed, etc.) via the MCP protocol, allowing an AI assistant to interact with Git repositories as if it were a developer at the command line.
The package is designed for automation and AI-assisted development workflows. It depends on gitpython for Git operations, mcp for protocol handling, pydantic for validation, and click for CLI argument parsing. It is currently in early development, meaning the tool set and behavior may change. Installation is straightforward via pip or uv, and configuration varies by host application (Claude Desktop, VS Code, Zed, etc.).
Use it for
- Let an LLM assistant read repository status, diffs, and logs to understand code changes and history without manual context-gathering.
- Automate commit workflows where an AI agent stages files, writes commit messages, and records changes based on analysis.
- Enable branch creation and switching via LLM commands for multi-branch development or experiment isolation.
- Query commit history with date filtering to analyze trends, blame, or revert decisions programmatically.
- Integrate Git operations into AI-driven code review or refactoring pipelines that need to inspect and modify repositories.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building LLM-integrated development tools or AI assistants that need programmatic Git access.
The package is actively maintained, has low install friction, and carries no security vulnerabilities. The MIT license poses no restrictions. The main caveat is that it is explicitly in early development—expect the tool set and behavior to evolve, and validate LLM-generated Git commands before execution in production repositories.
Install
mcp-server-git on PyPI
Before you install
Low friction install with a pure-Python wheel. Actively maintained with recent releases; last commit 2026-08-10. Requires Python 3.10+. Four runtime dependencies (click, gitpython, mcp, pydantic) are all stable, widely-used libraries.
Requires Python 3.10 or later. Git must be installed on the system. The server is designed to run as a background process managed by an MCP client (Claude Desktop, VS Code, Zed, etc.), not as a standalone library in your own Python code.
License in practice
MIT license is permissive—you can use, modify, and distribute this package freely with minimal restrictions, making it suitable for both open-source and commercial projects.
Quickstart
pip install mcp-server-git
# Run as a server (typically configured in Claude Desktop, VS Code, or Zed)
python -m mcp_server_git --repository /path/to/repo
# Or via uvx (recommended)
uvx mcp-server-git --repository /path/to/repoVerify before relying
- Whether the package handles large repositories efficiently or has known performance limits.
- Whether all Git operations (especially git_commit, git_add, git_reset) are safe to invoke from untrusted LLM outputs without additional validation.
- Stability guarantees beyond 'early development' status—what breaking changes are expected.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesclickgitpythonmcppydantic |
| Maintenance | Actively maintained 35 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 774,459 / month, #5,094 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10 |
Evidence: mcp_server_git-2026.7.10-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “git mcp server”
- mcp-server-gitExposes Git repository operations as tools for Large Language Models…
- airbyte-internal-opsProvides MCP (Model Context Protocol) server and CLI tools for…
- hol-guardHOL Guard is a local-first antivirus and runtime protection layer for…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also cli-mcp-server · mcp-server-fetch · mcp-server-time · mcp · mcp-server-appwrite · airbyte-internal-ops · tilt-mcp · wikipedia-mcp · blender-mcp · fastapi-mcp