GitKraken MCP Server

Gitkraken mcp server connects GitKraken to AI assistants that speak the Model Context Protocol. A CLI for interacting with GitKraken APIs. Includes an MCP server via gk mcp that not only wraps GitKraken APIs, but also Jira, GitHub, GitLab, and more.

What GitKraken does

gk is GitKraken on the command line. The core functionality is focused on "Work Items" which can be thought of as the feature or issue you are trying to tackle. This allows you to work with multiple repos at once and get the same UX as if you were in a monorepo. We also provide robust AI-powered commit messages and Pull Request generation. It also provides an MCP server that streamlines working with git and your Issue and git hosting providers.

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

• macOS — gk is available from Homebrew with the following command:
• Windows — gk is available from [Winget][winget] with the following command:

Installing the gitkraken mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. GitKraken sits in that group, and the shape of its toolset — macOS, Windows — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
• Written in Go.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the gitkraken mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.