Building An Mcp Server For Bitbucket: Connecting Llms To Your

Posted on Jan 8

• Originally published at javieraguilar.ai

After searching for an official MCP from Atlassian and not finding one, I decided to build my own. The existing community MCPs for Bitbucket were too limited—basic repository operations only, no pipeline support, no deployment management.

I needed something more complete for my daily workflow.

The Model Context Protocol (MCP) is a standard that allows LLMs to interact with external systems through a defined set of tools. Instead of copying and pasting between your IDE and Bitbucket's web interface, you can simply ask your AI assistant to handle it.

Context switching is expensive. Every time you leave your editor to check a pipeline, review a PR, or manage branch permissions, you lose focus. MCP eliminates that friction.

The MCP Server for Bitbucket exposes 58 tools covering the full Bitbucket API:

The power isn't in any single command—it's in the ability to chain operations naturally through conversation.

The server is available in both TypeScript and Python:

Authentication uses Bitbucket App Passwords, which you can create in your Bitbucket settings. The server respects rate limits and handles pagination automatically.

While GitHub has stronger native Claude support, many enterprise teams still rely on Bitbucket. This gap in tooling was exactly why I built this—and why I've open-sourced it for others in the same situation.

Source: Dev.to