git-mcp-server and gitlab-mcp
These are ecosystem siblings, as both projects implement the Model Context Protocol (MCP) to allow LLMs and AI agents to interact with Git repositories, with one specifically targeting general Git repositories and the other targeting GitLab.
About git-mcp-server
cyanheads/git-mcp-server
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management, and more, via the MCP standard. STDIO & HTTP.
This server helps AI agents or large language models (LLMs) manage code repositories. It allows them to perform common Git operations like cloning projects, committing changes, creating branches, merging code, and publishing updates. It's designed for developers who are building AI systems that need to interact with and modify source code.
About gitlab-mcp
mcpland/gitlab-mcp
A MCP server for GitLab with powerful, safe, policy-controlled access
Exposes 80+ tools across GitLab resources (MRs with code-context analysis, pipelines, wikis, releases, file management) via stdio or Streamable HTTP transports with flexible auth (OAuth 2.0 PKCE, PAT, remote token scripts, cookie-based). Enforces granular access control through read-only mode, tool allowlists/denylists, and project-scoped restrictions, while supporting enterprise networking (proxy, custom CAs, multi-instance rotation) and multiple output formats with size limits.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work