Think inside your AI world.

PlanetScale through Unl

PlanetScale's MCP server will list every open schema recommendation against a branch. Whether an unresolved one is a launch blocker or a someday-fix is your call - a suggestion sitting in a list isn't the same as a decision made about it.

PlanetScale through Unl reads branch schema and index recommendations against the deploy-readiness rule you have ratified, so 'can this branch go to production?' comes back solid-or-flag with the condition it hasn't met.

What PlanetScale holds

PlanetScale's hosted server, queried directly, surfaces:

  • read-only SQL query execution (SELECT, SHOW, DESCRIBE, EXPLAIN)
  • branch schema retrieval
  • schema recommendations, including missing indexes, redundant indexes, and primary key exhaustion
  • query performance insights per branch
  • organisation, database, and branch listings

What the naked read gives you

PlanetScale's MCP server runs the read-only query, pulls up the branch schema, and lists every open recommendation - the missing index here, the redundant one there, the primary key edging toward exhaustion. It surfaces the full picture of a database's health without ranking which recommendation matters enough to block a release.

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

What changes when PlanetScale is read measured

A database lead at a marketplace product ratified a deploy rule in Unl: no branch promotes to production while an open schema recommendation flags a table over a million rows, because an unindexed join on the orders table once doubled checkout latency for a week before anyone traced it.

'Can this branch go to production?' returns, measured: not yet - the schema recommendation read shows an unresolved missing-index suggestion on orders.customer_id, and that table already holds 2.3 million rows. PlanetScale supplied the recommendation; your ratified rule supplied the deploy bar.

And back again

Apply the missing index; PlanetScale through Unl picks up the cleared recommendation list the next time anyone asks, and the ratified deploy rule waves the branch through on that same page.

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 has to happen before this branch deploys?

Resolving the flagged recommendation - adding the missing index on orders.customer_id. Once the recommendation list comes back clean, the same ratified deploy rule reads the branch as production-ready.

How do I connect PlanetScale to Claude?

Authorise PlanetScale's hosted MCP server through OAuth from within Claude, scoping access to the organisations and databases you want visible. Unl reads through whatever that scope allows.

Does Unl write to my database?

No. Unl calls PlanetScale's read-only query and recommendation tools; destructive statements without a WHERE clause are blocked at the server level regardless. Any index change, you apply yourself.

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.