Local API and Model Context Protocol (MCP) for Tana!
Hey Product Hunt đź‘‹
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
No copy-paste. No re-explaining. The AI works from your real notes and structure.
Beyond slides, people are already using this for:
Reusable prompt libraries that evolve over time
Exploring large personal knowledge bases conversationally
Generating reports, summaries, and plans grounded in real context
Building AI-assisted workflows that write results back into Tana
Getting started
We’re also shipping a small optional skill pack for Claude Code, including:
A workspace understanding skill
A schema graph visualizer
A natural-language search builder
A slide deck generator
You can use the API directly, use MCP, or both. Documentation: https://tana.inc/docs/local-api-mcp
This is early, but intentional
We didn’t want to ship “just another integration.”
We wanted to make Tana a place AI tools can plug into as a system of record for thinking and knowledge.
We’d love feedback from builders, power users, and anyone experimenting with AI-native workflows:
What would you want AI to do with your notes?
What tools should Tana connect to next?
Happy to answer questions in the comments!
Replies