MCP server · Developer tools

Bitbucket MCP server

Lets your AI look at and manage your Bitbucket repos, pull requests, and pipelines for you.

Developer tools For it and development Version Control

This is a small helper that connects your AI assistant to Bitbucket, the place where your team keeps its code. Once it is set up, you can ask your AI things like what pull requests are waiting or why a build failed, and it will go and check for you. It is handy for anyone who works with code on Bitbucket but does not want to click through 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 an app. This one connects your AI to Bitbucket, so it can look up your repositories, pull requests, and pipelines, and do some things there when you ask. You set it up once, and after that your AI just uses it quietly in the background.

What this MCP server does

You ask your AI a question about your Bitbucket work, like which pull requests are open. The AI passes that request to this helper program. The helper talks to Bitbucket using your account details and a special password called a token. Bitbucket sends back the answer, and the helper hands it to your AI, which explains it to you in the chat. If you ask it to do something like merge a pull request or start a build, the helper carries that out too.

Flow diagram: you ask your AI “Which pull requests are open on Bitbucket?”, the Bitbucket MCP server connects it to Bitbucket, and you get back answers right in your chat.

Click to zoom

What you can do with it

List and search your repositories
Show open pull requests and their details
Create, approve, or merge a pull request
Check why a pipeline failed and read its logs
Start or stop a pipeline run
Browse files and folders without downloading the code
List branches, commits, tags, and deployments

What it gives back to you

You get answers in plain chat: lists of pull requests, branch names, commit messages, build results, or file contents. If you asked it to do something, like merge a pull request or start a pipeline, it tells you whether that worked. Longer things like logs or diffs come back as text you can read right there. You do not have to open Bitbucket yourself.

Before you start

What you need

A Bitbucket account with access to the workspace you want to use
An Atlassian API token (a kind of password for apps; you create it in your Atlassian account settings)
Your Bitbucket workspace name and the email address on your account
Node.js installed on your computer if you use the TypeScript version, or Python if you use the Python version

Good to know

It can change and delete real things in Bitbucket, like merging pull requests, deleting repositories or tags, and starting pipelines, so check what you ask it to do before you say yes.

Install it with your AI

Add Bitbucket MCP server 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, 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.