What authentication methods are supported?
Personal Access Token (recommended) and OAuth2 Token. The server checks for `GITLAB_OAUTH_TOKEN` first, then falls back to `GITLAB_TOKEN`.
@kopiloto
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"GitLab": {
"command": "uvx",
"args": [
"gitlab-mcp-server"
],
"env": {
"GITLAB_TOKEN": "<your GitLab personal access token>",
"GITLAB_URL": "https://gitlab.com"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
gitlab-mcp-server is an MCP server that integrates with GitLab using the python-gitlab library. It provides tools to read repository code, manage merge requests, and query project information. Intended for developers and CI/CD workflows, it authenticates via personal access tokens or OAuth2 tokens.
Install with uvx gitlab-mcp-server and configure the MCP client with environment variables GITLAB_TOKEN (or GITLAB_OAUTH_TOKEN) and GITLAB_URL. The server exposes tools that can be invoked directly from an MCP host (e.g., Claude Desktop) to interact with GitLab resources.
Personal Access Token (recommended) and OAuth2 Token. The server checks for `GITLAB_OAUTH_TOKEN` first, then falls back to `GITLAB_TOKEN`.
At minimum, the `read_api` scope is needed.
Yes. Set the `GITLAB_URL` environment variable to your instance URL (e.g., `https://gitlab.example.com`). If not set, it defaults to `https://gitlab.com`.
Yes. The default maximum is 50 files and 100 KB per file. Limits are configurable to prevent timeouts. Binary files are automatically detected.
No. The project is in **development stage**; features and APIs may change without notice. Use with caution in production environments.
MCP server connecting AI assistants with Jira & Confluence for smart project management.
GitHub's official MCP Server
Yuque mcp server
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed).
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).
评论