Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of GitLab MCP Server

GitLab MCP Server

Free Listing

A Model Context Protocol server for GitLab that lets MCP-compatible AI clients manage projects, merge requests, issues, pipelines, wikis, releases, tags, milestones, and more via GitLab REST and GraphQL APIs.

Visit zereight/gitlab-mcp

Overview

GitLab MCP Server connects MCP-compatible AI clients to GitLab through the Model Context Protocol. It provides tools for projects, merge requests, issues, pipelines, wikis, releases, tags, milestones, and related GitLab workflows, starting with 40 default tools and expanding through discover_tools to 288 total tools.

Key Features

  • Broad GitLab coverage across projects, repository browsing, merge requests, issues, pipelines, wiki, releases, tags, labels, and milestones.
  • Flexible authentication options include Personal Access Token, local OAuth2 browser flow, MCP OAuth proxy, and per-request remote authorization.
  • Supports stdio, SSE, and Streamable HTTP transports for local, legacy, and remote deployments.
  • Starts with a lean default toolset of 40 tools; discover_tools can activate additional toolsets for the session, with 288 tools total.
  • JMESPath result filtering and compact results help reduce oversized tool replies.
  • Self-hosted ready with custom GitLab instances, proxy settings, and dynamic API URL routing.

Use Cases

  • Review merge requests by listing changed files and fetching batched file diffs from an MCP-compatible AI client.
  • Inspect pipelines and retrieve paginated job logs without hunting through the GitLab UI.
  • Manage GitLab issues, projects, wikis, releases, tags, labels, and milestones through AI client workflows.
  • Run a hosted or self-hosted MCP endpoint for team or remote AI clients using Streamable HTTP.

Getting Started

  • Install the zereight-mcp-gitlab binary with npm or Homebrew, or use the npx one-liner.
  • Configure an MCP client with a GitLab Personal Access Token or OAuth2 settings.
  • Use the skill plus CLI path for workflows without MCP registration.

Deployment & Requirements

  • Node.js 20 or later is required.
  • A GitLab API URL and Personal Access Token or OAuth configuration must be supplied for the server to access GitLab.
  • Remote Claude.ai connections require public HTTPS and GITLAB_MCP_OAUTH on the server.
  • Shared HTTP deployments can expose a Streamable HTTP endpoint for remote clients.

Before You Adopt

  • License: MIT. Review its terms before using, modifying, or distributing the project.
  • The api toolset bypasses group/project allowlists, other tool filters, and per-tool safety checks, and prompt injection can drive it.
  • The @next npm build is a pre-release and is not intended for production use.

Comments

Sign in to leave a comment.

More like GitLab MCP Server

Favicon of GBrain

GBrain

Free ListingStars: 31.9K

A controllable shared memory layer for AI agents

MCP Servers & Tool Connectors

GBrain is a self-hostable memory layer for AI agents that stores sourced facts, supports corrections, and offers keyword, semantic, graph, and optional cited synthesis retrieval.

Favicon of HA-MCP

HA-MCP

Free ListingStars: 5.6K

Configure and automate Home Assistant with AI

MCP Servers & Tool Connectors

HA-MCP is a Model Context Protocol server that lets AI assistants like Claude and ChatGPT interact with Home Assistant. It supports device control, state queries, automations, dashboards, history, backups, and more through natural language.

Favicon of PipesHub

PipesHub

Free ListingStars: 4K

Open-source, permission-aware context for AI agents

MCP Servers & Tool Connectors

PipesHub is an open-source context layer for AI agents that turns company knowledge from connected business systems into permission-aware search and cited answers, with self-hosted deployment and SDK/MCP access.