How do I authenticate with Gitkraken?
Run `gk auth login` to authenticate with the GitKraken platform. You can also manage provider tokens with `gk provider`.
@gitkraken
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": {
"gitkraken": {
"command": "gk",
"args": [
"mcp"
]
}
}
}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。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
GitKraken CLI (gk) is a command‑line tool that provides GitKraken’s features on the terminal. It focuses on “Work Items” (features or issues) to manage multiple repositories as if they were a monorepo, offers AI‑powered commit messages and Pull Request generation, and includes a local MCP server that wraps git, GitHub, Jira, and GitKraken APIs for use with LLMs.
Install via Homebrew (macOS), Snap/.deb/.rpm (Unix), Winget (Windows), or download from the releases page. Authenticate with gk auth login, then navigate to a repository, create a work item with gk work create, edit files, commit with gk work commit --ai, push with gk work push, and create a PR with gk work pr create --ai. Use gk help for all commands. For MCP server setup, follow the instructions in the Help Center.
Run `gk auth login` to authenticate with the GitKraken platform. You can also manage provider tokens with `gk provider`.
This is caused by browsers (like Safari or Brave) blocking the redirect to localhost port 1314. Change your default browser or copy the URL and open it in another browser.
Oh‑My‑Zsh aliases `gitk` as `gk`. Run `unalias gk` to resolve the conflict.
Download the binary from the releases page, move it to `/usr/local/bin/gk`, then go to Settings > Security & Privacy > General and click “Allow Anyway” if a security error appears.
Specific installation instructions for your chosen AI application are available in the [GitKraken Help Center](https://help.gitkraken.com/cli/gk-cli-mcp/).

Remote MCP server for Mythex, an AI app builder. Claude, Cursor or Codex get a cloud sandbox to build full-stack apps: files and bash, live preview, Postgres database, file storage, secrets, checkpoints, browser tests an
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
评论