MCPs for GitHub, GitLab, and Git workflows
Version control MCP servers expose Git hosting APIs (GitHub, GitLab) to agents — branches, PRs, issues, reviews, merges. Claude Code, Cursor, and every AI coding tool relies on these. Pair with file-ops for full dev-loop automation.
Version control MCPs connect agents to GitHub, GitLab, Bitbucket, and Gitea. Agents can read code, create branches, open PRs, review diffs, merge changes, and manage issues — the foundation of every coding agent.
Every push to main triggers a Supabase migration automatically. Schema diffs are committed and applied with zero manual steps.
Open a PR and a Vercel preview URL appears as a comment within minutes. Branches are cleaned up automatically when PRs close.
A Linear issue assigned to a developer automatically creates a git branch, syncs status changes, and opens a draft PR.
Tests run on every push. Failures post a Slack message with the failing test name, screenshot, and a link to the run.
SonarQube analyzes every PR for code smells, coverage drops, and security hotspots. PRs below the quality gate are blocked.
Yes, but respect branch protection rules. Most teams require human approval + passing CI before merge — the MCP honors both.
The MCP exposes GitHub as structured tools with schemas, so the LLM knows exactly what args to pass. `gh` is a CLI — the MCP wraps that into typed tool calls.
Yes for core workflows (branches, PRs, issues). Some advanced features (GitHub Actions ≠ GitLab CI) are vendor-specific.
Yes — use a fine-grained GitHub token scoped to specific repos and permissions (no admin, no org-wide).
Browse the full marketplace or explore all tags to find the right MCPs for your stack.