How does Custom GitLab MCP Server differ from the standard GitLab MCP server?
It fixes schema validation issues present in the standard implementation, specifically for the `search_repositories` tool.
@chris-miaskowski
基本情報
概要はまだありません
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
Custom GitLab MCP Server is an implementation of the Model Context Protocol (MCP) that enables AI assistants like Claude to interact with GitLab repositories. It fixes schema validation issues present in the standard GitLab MCP server, specifically for the search_repositories tool. This server is for developers who want to search, read, create, and update GitLab resources through AI-powered workflows.
Clone the repository, run npm install, then configure the server in your Claude settings file (either claude_desktop_config.json or the application settings JSON). Set the command to node, provide the path to index.js, and supply environment variables GITLAB_PERSONAL_ACCESS_TOKEN and GITLAB_API_URL (pointing to your GitLab instance). No additional invocation commands beyond the standard MCP server configuration are documented.
It fixes schema validation issues present in the standard implementation, specifically for the `search_repositories` tool.
Node.js version 14 or higher is required. You also need a GitLab Personal Access Token with appropriate scopes.
Use `api` for full API access, `read_api` for read‑only access, and `read_repository` / `write_repository` for repository operations.
It connects to any GitLab instance via the `GITLAB_API_URL` environment variable (e.g., `https://your-gitlab-instance/api/v4`).
The server uses standard MCP transport as configured in the Claude settings file; it is started as a child process with environment variables.
A Go-based MCP (Model Control Protocol) connector for Jira that enables AI assistants like Claude to interact with Atlassian Jira. This tool provides a seamless interface for AI models to perform common Jira operations including issue management, sprint planning, and workflow tra
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed).

Model Context Protocol Servers
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs

Model Context Protocol Servers
コメント