"Git" matching MCP servers:

An MCP server that gives AI agents a full, safe interface to Git with automatic backups, isolated worktrees, and structured JSON outputs.

Connects AI tools to GitHub and local git repositories, enabling natural language management of issues, PRs, code analysis, and workflows.

AI code reviews and git activity digests with machine-readable risk scoring, available as an MCP server for use within an agent session.

Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (42 meta-tools / 57 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.

GitHub's official MCP Server

Provides git-aware safe file operations, allowing AI agents to delete files while protecting git-tracked source code from accidental deletion.

Suggests the latest stable package versions when writing code.

A self-hosted MCP server that provides capability packs for AI agents to perform browser, desktop, git, and code actions via schema-validated JSON calls, enabling reliable agentic workflows even with small open-weight models.

Enables an assistant to work inside gitlab.com projects as the signed-in user: issues, merge requests, code reviews, repositories, CI pipelines and job logs, plus optional gated toolsets for wiki, snippets, releases, planning, deployments and activity. It authenticates through a user-supplied OAuth application with the token kept in the OS keyring, and registers only the tools that are switched on.

A single static Go binary that exposes GitHub operations (repos, branches, commits, file contents, issues, PRs, and search) as MCP tools, enabling agents to read and write GitHub data with no runtime dependencies.

MCP server that helps coding agents research and prepare GitHub contributions by gathering repository guidance, related work, code context, and validation evidence into a local SQLite corpus, without ever writing to GitHub.

Gitee API integration, repository, issue, and pull request management, and more.

Local-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.

Enables ChatGPT on Windows to securely access codebases, Git, terminals, language servers, debuggers, SQLite, local HTTP services, adaptive project memory, engineering skills, checkpoints, audit logs, and sandboxed command execution through MCP tools.

Summarizes GitHub discussions, issues, and pull requests by storing data locally for fast, token-efficient responses.

Enables autonomous coding agents to inspect Git commits, create pull requests, parse issue threads, and post reviews on GitHub repositories.

Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.

Local CI/CD engine for AI agents. ActionD listens to LGH git events and runs plugin jobs (Go/Python/Java/web toolchains) in isolated checkouts, with structured results, root-cause failure diagnosis, approval gates, and auto-rollback. The MCP server exposes 23 tools, including dev_cycle_run (commit → CI → structured verdict in one call) and actiond_diagnose for failed-job analysis.

Local-first Git hosting for AI coding agents. lgh serve turns any directory into an HTTP Git remote (127.0.0.1:9418) with push events, commit-status reporting, smart .gitignore generation, secret/large-file detection, and optional LAN sharing with auth. The MCP server exposes 10 tools covering repo registration, one-command backup (lgh up), server control, and event access.

Coordination for parallel coding agents: TTL file claims stored in the git common dir (visible across all worktrees), enforcement hooks that block colliding edits, agent presence, handoff notes, and a git-committed lessons knowledge base with BM25 search. Single static Go binary — no server, no database.