MCP server · Developer tools

Bitbucket MCP server (bbkt)

Lets your AI look at and work with your Bitbucket Cloud repos, pull requests, pipelines and issues.

Developer tools For it and development Version Control

This is a small helper program called bbkt that connects your AI assistant to Bitbucket Cloud, the place where your team keeps code and reviews changes. Once it is set up, you can ask your AI things like which pull requests are open or why a build failed, and it will go and check for you. It is handy for anyone who works with a Bitbucket repo but does not want to click around the website all day.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app. This one connects your AI to Bitbucket Cloud, so when you ask a question about your repos or pull requests, the AI can actually go and look. You install it once, tell your AI app about it, and after that it just works in the background.

What this MCP server does

You ask your AI something about your Bitbucket work, like what pull requests are waiting for review. The AI passes that request to this helper program. The helper talks to Bitbucket Cloud using your account, fetches the answer, and hands it back to the AI. The AI then explains it to you in the chat, in plain words. For write actions, like creating a pull request or triggering a build, the helper makes the change on Bitbucket and tells the AI it is done.

Flow diagram: you ask your AI “What pull requests are open in my repo?”, the Bitbucket MCP server (bbkt) connects it to Bitbucket Cloud, and you get back answer in plain words.

Click to zoom

What you can do with it

List your workspaces and repositories
Show open, merged or declined pull requests
Create, approve, merge or decline a pull request
Read, search and even write files in your repo
List and trigger pipelines, and read their logs
List, create and update issues
Add and resolve comments on a pull request

Try asking your AI

“What pull requests are open in my repo right now?”
“Show me the last failed pipeline and why it failed”
“Create a pull request from my branch feature/login into main”
“Read the README file on the main branch”

What it gives back to you

You get answers in the chat, in normal sentences. For lists, like pull requests or pipelines, you get a short summary with names, statuses and links. For files, you get the file content. For actions, like creating a pull request or triggering a build, you get a short confirmation that it was done, sometimes with a link to the new thing.

Before you start

What you need

A Bitbucket Cloud account with access to at least one workspace
An Atlassian API token with the right scopes (a kind of password for apps; you create it on the Atlassian website)
The bbkt program installed on your computer
An AI app that supports MCP servers, like Claude Desktop or Cursor

Good to know

It can change things on Bitbucket, like creating pull requests, writing files or triggering builds, so check what your AI is about to do before saying yes.

Install it with your AI

Add Bitbucket MCP server (bbkt) to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Bitbucket MCP server (bbkt), install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.