MCP server · Developer tools

Bitbucket MCP server

Let your AI read Bitbucket pull requests, diffs and comments, and post review comments or approvals for you.

Developer tools Coding For it and development Version Control

This is a small helper that connects your AI assistant to Bitbucket Cloud, the place where your team keeps code and reviews pull requests. Once it is set up, you can ask your AI to look at a pull request, explain the changes, and even leave a comment or approve it. It is handy for developers and anyone who reviews code on Bitbucket and wants a first pass done quickly.

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 or service. This one connects your AI to Bitbucket Cloud, so it can look up pull requests, read the changes, and post comments there when you ask. You stay in the chat; the helper does the talking to Bitbucket.

What this MCP server does

You ask your AI something like "show me the open pull requests in my workspace". The AI passes that request to this helper. The helper talks to Bitbucket Cloud using your account details and a token. Bitbucket sends back the list, the diff, the comments, or whatever you asked for. If you ask it to comment or approve, the helper sends that change to Bitbucket and tells you it is done.

Flow diagram: you ask your AI “Show the open pull requests in my workspace”, the Bitbucket MCP server connects it to Bitbucket, and you get back answers in your chat.

Click to zoom

What you can do with it

List repositories in your Bitbucket workspace
List pull requests by state (open, merged, declined, superseded)
Read a pull request's description, branches, reviewers and approvals
Fetch the diff of a pull request so your AI can review it
Read existing comments on a pull request, general and inline
Browse the file tree and read file contents at a branch or commit
Post a comment, approve, or request changes on a pull request

Try asking your AI

“List the open pull requests in my Bitbucket workspace”
“Show me the diff for pull request 42 and summarize what changed”
“Read the comments on pull request 42 and tell me what reviewers are asking for”
“Post a comment on pull request 42 saying the tests need updating”

What it gives back to you

You get answers in the chat: lists of repositories or pull requests, the diff text, existing comments, commit history, or file contents. When you ask it to comment or approve, it tells you the action was sent to Bitbucket. Everything shows up as normal chat text you can read and copy.

Before you start

What you need

A Bitbucket Cloud account with access to the workspace you want to review
An API token from Bitbucket with the right scopes (read repositories, read pull requests, write pull requests)
Your Atlassian account email (the one tied to Bitbucket)
Node.js installed on your computer, plus the Claude desktop app or Claude Code

Good to know

The token can read and change pull requests in your workspace, so keep it secret and consider a read-only token if you only want suggestions, not comments or approvals.

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.