Think inside your AI world.
Mintlify through Unl
Search results and page content, read straight from the docs site, then checked against the citation rule you actually ratified.
Mintlify through Unl reads docs-search results against the citation criteria you have ratified, so 'does the docs answer this' comes back supported, not settled, with the condition it hasn't met.
What Mintlify holds
Mintlify through Unl reads what the docs site already indexes:
- Searches across the site and returns matching content with titles and links
- Reads and navigates the site's own content structure using filesystem-style commands
- Returns snippets tied to a specific page, not a paraphrase
- Confirmed read-only and non-destructive by the server's own tool annotations
What the naked read gives you
Ask Mintlify's own MCP server to find the answer to a support question and it searches the live docs directly, returning the actual page and the actual snippet, not a summary from months-old memory. It's a fast, literal, well-cited read of what the documentation currently says.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Mintlify is read measured
A developer relations lead ratified that a support answer only counts as supported if the cited page was updated after the last major version release, because an old auth example kept getting quoted back at customers a full version behind.
'Does the docs answer this question?' returns, measured: supported, not settled, because Mintlify's own search surfaces a matching page, but its last-updated date sits before the ratified release cutoff. Mintlify supplied the search result and page date; your ratified rule supplied the release-cutoff condition.
And back again
The distinction between a match and a settled answer doesn't reset with every new ticket — Unl keeps the search result, the page date and the ratified cutoff together, so the same question from a different customer starts from a known position, not a fresh search.
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 settles an answer that started out only supported?
A cited page updated after the release cutoff the rule sets. Once Mintlify's own search surfaces a page with that later date, the same question returns settled - the citation rule hasn't moved, the page has.
How do I connect Mintlify to Claude?
Mintlify generates a search MCP server automatically for any Mintlify-hosted docs site; add its endpoint as an MCP connector in Claude Code with a command such as claude mcp add, pointing at the site's own MCP URL. Its search and filesystem-read tools then become a source Unl can query.
Does Unl change anything on the Mintlify docs site?
No. The server's own tool annotations mark it read-only and non-destructive - nothing on the docs site is edited or restructured 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.