Think inside your AI world.

Sanity through Unl

Documents, datasets and schemas, read straight from the project, then checked against the publishing rule you actually ratified.

Sanity through Unl reads document, schema and dataset state against the publishing criteria you have ratified, so 'is this entry ready to publish' comes back pending, not passed, with the condition it hasn't met.

What Sanity holds

Sanity through Unl reads what the project already holds:

  • Fetches a single document by its exact ID
  • Queries documents using GROQ, filtering and combining fields across a dataset
  • Fetches the deployed schema for a workspace, resolving the current live source
  • Lists datasets within a project and lists the projects an account can access
  • Runs semantic search across content and across Sanity's own documentation

What the naked read gives you

Ask Sanity's own MCP server what a content entry currently contains and it queries the dataset directly with GROQ, returning the actual fields against the actual schema, not a guess at structure. It's an exact, queryable read of the content as it stands in the project right now.

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

What changes when Sanity is read measured

A content ops lead ratified that an entry stays unpublished without every schema-required field populated and a named editor's sign-off recorded, because a launch page once went live missing its legally required disclosure field.

'Is this entry ready to publish?' returns, measured: pending, not passed, because Sanity's own GROQ query shows every required field populated but no editor sign-off recorded against the document. Sanity supplied the document and schema read; your ratified rule supplied the sign-off condition.

And back again

That single missing sign-off doesn't have to be tracked down again by the next person who opens the entry — Unl keeps the document read and the outstanding condition attached to it, so the check picks up exactly where it stopped.

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 passes an entry that's currently only pending?

An editor's sign-off recorded against the document. Once Sanity's own document read shows that field populated alongside the required content fields, the same question returns passed - the publishing rule hasn't moved, the document has.

How do I connect Sanity to Claude?

Connect to the remote Sanity MCP server at mcp.sanity.io, authenticate with OAuth against your Sanity project, and add it as an MCP connector in Claude Code or Claude Desktop. Its document, schema, dataset and query tools then become read sources Unl can query.

Does Unl change anything in my Sanity project?

No. The connection only reads - documents, schemas, datasets, queries. Nothing is created, edited or published as a result of a measured answer.

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.