Think inside your AI world.

Shortcut through Unl

Shortcut shows the epic and how many of its stories are marked complete. Whether it's actually ready to ship is your call - a high completion percentage can still be hiding a blocked story.

Shortcut through Unl reads stories, epics and their states against the shippable criterion you have ratified, so 'is this epic ready to ship' comes back done-or-not with the condition it hasn't met.

What Shortcut holds

Shortcut's official MCP server exposes:

  • stories-search - find stories with filtering and search options
  • stories-get-by-id - get a single story by ID, including its current state
  • epics-search - find epics and their associated stories
  • stories-get-branch-name - get the recommended branch name tied to workspace settings for a story

What the naked read gives you

Ask Shortcut's own MCP how the billing-refactor epic is doing and it counts the stories: eleven of twelve marked done, one still in progress. That's a correct read of the epic's state. What it doesn't say is whether that one remaining story is quietly blocked on a dependency nobody's chased, which would mean the epic isn't a day from shipping, it's stuck. Shortcut counts stories accurately; whether the count means the epic is actually shippable is a separate question entirely.

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

What changes when Shortcut is read measured

Say you're the delivery lead, and you have ratified this in Unl: an epic is shippable only when every story inside it is done and none sits flagged as blocked - because eleven of twelve is still zero of twelve when the twelfth is stuck.

'Is the billing-refactor epic shippable' returns, measured: not met - eleven stories are done, but the twelfth is marked blocked pending a database migration. Shortcut supplied the story states and the blocked flag; your ratified rule supplied the shippable criterion.

And back again

That verdict is itself ratified into Unl, so 'shippable' now carries a fixed meaning for this team - every later status check tests each story's state against it, rather than trusting a completion percentage that quietly hides the one blocked story.

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

Can Shortcut tell me if an epic is actually shippable?

Shortcut's MCP returns each story's state and any blocked flags; it doesn't decide what shippable requires. That's the criterion you ratified in Unl, which turns the story read into a verdict.

How do I connect Shortcut to Claude?

Shortcut runs an official hosted MCP server at mcp.shortcut.com - authentication is handled through OAuth, so there's no API token or local server to set up before Claude can connect.

Does connecting Shortcut let Unl update my stories?

No - Unl reads the stories, epics and states Shortcut's MCP exposes. It doesn't move stories or change their status on your behalf.

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.