Think inside your AI world.

Bitbucket through Unl

Bitbucket's MCP server will list every open task still sitting on a pull request. Whether an open task is reason enough to hold the merge is a bar you've set once already, after the wrong one got missed.

Bitbucket through Unl reads a pull request's open task list against the merge-hygiene rule you have ratified, so 'are all the review tasks actually closed?' comes back pending with the condition it hasn't met.

What Bitbucket holds

Ask Bitbucket's MCP server about a pull request and it returns:

  • a list of pull requests in a repository
  • full details on a specific pull request
  • comments left on a pull request
  • tasks attached to a pull request, open or resolved
  • analysis of why a pipeline step or commit status failed

What the naked read gives you

Bitbucket's MCP server lists a repository's pull requests, fetches full details on one, reads its comments, and pulls the tasks attached to it - the checklist items reviewers raise that need resolving before merge. It can also analyse why a commit status or pipeline step failed. It reports the state of every task precisely, open or resolved, without deciding whether an open one should stop a merge.

The frame judges the data it is given; it does not verify the source’s accuracy.

What changes when Bitbucket is read measured

An engineering manager at a SaaS billing company ratified a merge-hygiene rule in Unl: no pull request merges while it still carries an open, unresolved task, because a PR once merged with an open task reading 'add rate-limiting before merge' still sitting unaddressed, and the missing limiter contributed to an outage two weeks later.

'Are all the review tasks actually closed on this PR?' returns, measured: not yet - the task read shows one open task on pull request #482, the same rate-limiting note, still unresolved after nine days. Bitbucket supplied the task list; your ratified rule supplied the merge-hygiene bar.

And back again

Resolving the open task is the only move here. Bitbucket through Unl finds the task list empty on its next look, and the merge-hygiene rule waves the pull request through on the page that's already up.

The answer comes back measured against what you already decided, and why.

The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.

Questions people ask

What would clear this pull request to merge?

Resolving the outstanding task - in this case, implementing or explicitly waiving the rate-limiting note. The same ratified rule reads the closed task list and clears the merge.

How do I connect Bitbucket to Claude?

Connect Atlassian's official remote MCP server to Claude and authorise Bitbucket Cloud access via an API token - Bitbucket tools currently require token authentication rather than OAuth. Unl's reads run through that same connection.

Does Unl write to my repository?

No. Unl calls Bitbucket's getPullRequests, getPullRequestDetails, and getPullRequestTasks tools to see current state; it opens no pull requests and resolves no tasks. Any resolution, your reviewer makes it.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.