"A guide to managing GitLab projects" matching MCP servers:

MCP server that acts as a thin proxy over GitLab REST API v4, enabling users to list merge requests, view diffs, and leave inline comments without leaving their MCP client.

The Token-Curated GitLab MCP Server: 80%+ Context Window Savings. Every time your agent fetches a pipeline with other servers, it wastes 1,600 tokens of avatar URLs, internal links, and HTML fluff. With @sumirati/mcp-gitlab, that drops from 1,840 to 190 tokens.

MCP server for GitLab that enables AI assistants to manage CI pipelines, job logs, repositories, branches, merge requests, and commits via the GitLab REST API.

First gitlab mcp for you, building together

Enables AI agents to access and manage project guidelines, documentation, and context through a structured content system with template support and workflow management.

Enables an MCP client to drive the merge-request review workflow on a self-hosted GitLab CE 11.3 instance: list and create merge requests, read per-file diffs, post comments on exact diff lines, reply to and resolve threads, and merge. It also exposes read-only helpers for projects, branches, files, users, labels, pipelines and an escape-hatch raw API call, honoring a read-only mode.

Enables AI assistants to manage GitLab issues, merge requests, pipelines, and access the REST API via the glab CLI.

Enables AI agents to read GitHub Projects v2 boards over stdio, letting them list projects and their items across repositories so cross-repository work can be coordinated without scanning every repository. The read-only MVP authenticates via a GitHub App installation token minted at runtime and exposes list_projects, get_project, and list_project_items tools with cursor-based pagination.

A Model Context Protocol server that enables AI assistants to interact with self-hosted GitLab instances through 30 specialized tools. It supports managing projects, merge requests, CI/CD pipelines, and repository operations via the GitLab REST API v4.

A production-ready MCP server for GitLab enabling AI assistants to read and manage GitLab projects, merge requests, issues, pipelines, wikis, releases, and more through a unified interface.

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.

MCP server for GitLab CI/CD — pipelines, jobs, schedules, branches, tags, merge requests and repository files. Works with any GitLab (SaaS gitlab.com or self-hosted) via python-gitlab.

Enables Claude Code to read, create, update, and delete Claude Cowork/claude.ai projects and their knowledge documents, including syncing local folders to projects, with safety features like backups and overwrite protection.

Enables retrieving comprehensive information about GitLab merge requests, including details, commits, diffs, discussions, approvals, and CI/CD status, through natural language.

Connects AI assistants to GitLab to interact with merge requests, reviews, discussions, pipelines, and test results through natural language queries. Supports viewing MR details, responding to comments, checking test summaries, and analyzing job logs.

Enables interaction with GitLab projects, merge requests, issues, and code reviews through Claude AI, providing tools for code review and project management.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables AI assistants to manage GitHub Projects V2, including items, fields, and views through a standardized interface.

An MCP server that transforms books into agent-callable skill packages, enabling AI agents to use books as guides for evidence, procedures, and tutoring.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.