MCP server
GitLab MCP server
GitLab's built-in MCP server lets AI read projects, code, merge requests and pipelines and create commits and work items. In beta.
- Official server
- Developer tools
At a glance
- Maintained by
- GitLab
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
GitLab is a complete software delivery platform: code, merge requests, pipelines and planning. GitLab now builds its MCP server into the platform itself, reached at an address on your GitLab instance and signed in with OAuth. An assistant can read projects, files, merge requests and pipeline jobs, and can create commits, merge requests and work items.
Pipeline access is especially useful: an assistant can look at a failed job, read the log and suggest what went wrong.
The server is labeled beta at review time. The older MCP reference server for GitLab is archived. Because sign-in uses your GitLab account, the assistant has the same access you do, so use an account with only the projects a task needs when working with agents.
Use cases
Best business use cases
Failed pipeline help
Merge request summaries
Code questions
Status reports
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: reads projects, code, MRs and pipelines, and can commit, open MRs and create work items.
-
get_projectGet metadata for a GitLab project.
-
list_merge_requestsList or search merge requests in a project or group.
-
get_merge_requestGet a merge request with optional diffs, commits, notes or pipelines.
-
save_merge_requestCreate or update a merge request.
-
get_repository_fileGet a file's contents at a specific ref.
-
add_commitCommit a batch of file changes to a branch.
-
list_pipelinesList CI/CD pipelines in a project.
-
get_pipeline_jobsGet the jobs for a pipeline.
-
save_work_itemCreate or update an issue or other work item.
-
searchSearch for a term across the GitLab instance.
Workflows
Example workflows
Investigate a failed pipeline
-
1
A pipeline fails on main.
-
2
The assistant lists the failed jobs.
-
3
It reads the job logs.
-
4
It explains the likely cause.
-
5
A developer applies and reviews the fix.
Turn notes into work items
-
1
Paste meeting notes.
-
2
The assistant extracts actions.
-
3
It drafts work items with owners.
-
4
You approve the list.
-
5
It creates the items in the project.
Prompts
Example prompts
“Why did the latest pipeline on main fail? Read the job logs.”
“Summarize open merge requests in this project and who is reviewing each.”
“Create work items for these action points and assign them.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"GitLab": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://<gitlab.example.com>/api/v4/mcp"
]
}
}
}Claude Code: terminal
claude mcp add -s user --transport http GitLab https://gitlab.com/api/v4/mcp- Hosted server: streamable-http; https://gitlab.com/api/v4/mcp; https://<gitlab.example.com>/api/v4/mcp; OAuth 2.0 with dynamic client registration.
- Local server: stdio via mcp-remote proxy; mcp-remote.
- Needs: None in config; OAuth sign-in on first connect. Requires Node.js 20+ for mcp-remote in Claude Desktop..
Security
Security considerations
-
Account scope
The assistant has your account's access. Use limited accounts for agents.
-
Beta status
The server is in beta. Test before relying on it.
-
Protected branches
Keep protection and approvals on.
-
Untrusted text
Treat issue and log content as data, not instructions.
Related servers
Servers that pair well with it
GitHub
GitHub's official MCP server lets AI read repositories, search code, manage issues and pull requests and, when allowed, change files.
Git
The MCP project's Git reference server lets AI read history and diffs and stage, commit and switch branches in a local repository.
Jira
Atlassian's official Rovo MCP server lets AI search, create and update Jira issues and search, read and create Confluence content.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI copilots AI helpers built into your product or internal tools that draft, summarize and suggest while people decide.
- MVP development A first version with just enough features to put in front of real users and learn what to build next.
- Internal tools Custom software for your own team: trackers, approval flows and back-office systems that replace spreadsheets.
- Business process automation Map a process that runs on email and spreadsheets and turn it into software with clear steps and owners.
- Legacy modernization Replace an aging system step by step, with the business running normally while the new parts take over.
Solutions
View all solutions- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Approval workflows Requests, approvals and reminders in one place, with clear owners and deadlines instead of long email threads.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- AI-assisted content workflows Briefs, first drafts, edits and repurposing in a workflow where people set the angle and approve every word.
Industries
View all industriesGuides and articles
View all guides and articles- Where AI helps in development, and where it does not An honest map of the development tasks AI speeds up and the ones that still need experienced people.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- What is AI-accelerated development? How software teams use AI to plan, code, test and document faster, and where people still make every decision.
- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Mistral Medium 3.5 A newer open-weight Mistral model for agent and coding work, with image input, tool calling, structured outputs and a 256K window.
- Codestral 25.08 Mistral's low-latency coding model for code completion and generation, with fill-in-the-middle support, tool calling and a 128K window.
- Qwen3-Coder Qwen's open-weight coding models under Apache 2.0, from the efficient Qwen3-Coder-Next to the large 480B model, with tool use and long context.
- Coding Models that write, review and explain code, and power coding assistants and developer tools.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Sol The middle model of the GPT-6 family, positioned for complex coding and agentic workflows at a mid price level.
Glossary terms
View all glossary terms- AI copilot An AI copilot is an assistant built into a tool people already use, which suggests, drafts and explains while the person stays in control.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- Claude Code Claude Code is Anthropic's agentic coding tool, which works in a developer's terminal, IDE, desktop app or browser to read code, run commands and make changes.
- Automation Automation is using software to perform a task or process with little or no human effort each time it runs.
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is built into GitLab and was in beta at review time.
With OAuth through your GitLab account.
It is served from your GitLab instance. Check the GitLab docs for version requirements.