Custom GitLab MCP Server

@MCP-Mirror

Repository

Basic information

About Custom GitLab MCP Server

Mirror of

#gitlab #mcp-server #ai-integration

Custom GitLab MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Custom GitLab MCP Server tools

Search for GitLab projects

Get contents of a file or directory

Create or update a single file

Push multiple files in a single commit

Create a new GitLab project

Create a new issue

Create a new merge request

Fork a project

Create a new branch

Overview

What is Custom GitLab MCP Server?

This server is a custom implementation of the GitLab MCP (Model Context Protocol) server for integration with Claude and other MCP-compliant AI assistants. It fixes schema validation issues present in the standard GitLab MCP server and enables AI assistants to search repositories, fetch file contents, create/update files, push multiple files in a single commit, create issues and merge requests, fork repositories, and create branches.

How to use Custom GitLab MCP Server?

Clone the repository, run npm install to install dependencies, then configure the server in your Claude settings file or Claude Desktop config under the mcpServers key with the GITLAB_PERSONAL_ACCESS_TOKEN and GITLAB_API_URL environment variables.

Key features of Custom GitLab MCP Server

Search for GitLab projects
Get file or directory contents
Create or update a single file
Push multiple files in one commit
Create new GitLab projects
Create issues and merge requests

Use cases of Custom GitLab MCP Server

Search GitLab repositories from an AI assistant
Retrieve file contents for analysis or editing
Create or update files in a GitLab repository
Push multiple files in a single commit via AI
Create issues and merge requests programmatically

Frequently asked questions

What does this custom server fix?

It fixes schema validation issues with the `search_repositories` tool that were present in the standard GitLab MCP server implementation.

What are the prerequisites for using Custom GitLab MCP Server?

Node.js v14 or higher and a GitLab Personal Access Token with appropriate scopes: `api` for full access, `read_api` for read-only, `read_repository` and `write_repository` for repository operations.

How do I configure Custom GitLab MCP Server?

Add it to your Claude settings file under `mcpServers` with the command to run the server using Node.js and provide the environment variables `GITLAB_PERSONAL_ACCESS_TOKEN` and `GITLAB_API_URL`.

What tools does Custom GitLab MCP Server provide?

It offers nine tools: `search_repositories`, `get_file_contents`, `create_or_update_file`, `push_files`, `create_repository`, `create_issue`, `create_merge_request`, `fork_repository`, and `create_branch`.

What environment variables are required?

`GITLAB_PERSONAL_ACCESS_TOKEN` for authentication and `GITLAB_API_URL` pointing to your GitLab instance's API endpoint (e.g., `https://your-gitlab-instance/api/v4`).

Comments

More Version Control MCP servers

Github Mcp Server

github

GitHub's official MCP Server

31.3K

Gerrit Review MCP Server

cayirtepeomer

This MCP server provides integration with Gerrit code review system, allowing AI assistants to review code changes and their details through a simple interface.

MCP Linear

tacticlaunch

MCP server that enables AI assistants to interact with Linear project management system through natural language, allowing users to retrieve, create, and update issues, projects, and teams.

141

Atlassian Data Center MCP

b1ff

MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version

Join Cloud

kushneryk

Join.cloud lets AI agents work together in real-time rooms. Agents join a room, exchange messages, commit files to shared storage, and optionally review each other's work — all through standard protocols (MCP and A2A).