Hey Product Hunt
We just shipped something we ve wanted to build for a long time: a local API and Model Context Protocol (MCP) integration for Tana.
The short version:
 AI tools like Claude Code can now read, reason over, and write back to your actual Tana workspace including structured notes, outlines, prompts, and relationships instead of working on pasted text or one-off prompts.
Why we built this
Most AI workflows today look like this:

• Copy something out of your notes

• Paste it into a chat or terminal

• Lose context

• Start over next time

That s not how real work compounds.
Tana is designed as a permanent, structured thinking system. With the new API + MCP, AI tools can finally work inside that system instead of around it.
What this unlocks
A simple example we re excited about:

• Capture a voice memo in Tana

• Shape it into an outline using the editor

• Let Claude Code turn that structured note into a slide deck

Folks often think of Tana as having a "steep learning curve." And I get where that comes from it's flexible and powerful, so there are a lot of different ways to set up workflows. But there's a specific relationship between supertags, fields, and searches that is simple to learn that I consider my fundamental Tana LEGO block.

It works like this. If I want to see how two things relate say, books and authors I first create supertags for both. Then within the #book supertag I create a field called "Author" that draws its options from instances of the #author supertag. And in the #author supertag, I create a search called Books that finds all books by whatever author you're looking at.