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
Quick background: we're the team behind Trickle.so, where we help people build apps and websites with AI. We've been deep in the AI tooling space for a while now, and something kept bugging us.
Every feed today claims to be better curated or more relevant. But most of them still measure success by how long you stay.
I ve caught myself opening Twitter or YouTube to check one specific thing, then resurfacing 30 45 minutes later,
wondering where the time went.
Curious how this plays out for others here. When you open a feed for a quick check, how long do you actually stay? And does it usually feel worth it after?
This debate often gets framed as Should researchers use AI for literature reviews?
I think the real question is different.
Is it ethical to spend hundreds of researcher hours on mechanical work when that time could be spent advancing actual knowledge?
Think about a researcher spending an entire weekend searching papers, skimming irrelevant abstracts, copying citations, and fixing references. That s not insight or discovery. That s overhead.
