Notion is the most common knowledge surface Actionist writes into. Use it as a daily digest destination, a CRM-lite, a project hub, or the long-term memory for an agent.Documentation Index
Fetch the complete documentation index at: https://learn.actionist.ai/llms.txt
Use this file to discover all available pages before exploring further.
What you can do
- Create pages in any database with structured properties (status, owner, dates, relations).
- Query databases with filters, sorts, and pagination.
- Append blocks (text, callouts, toggles, code, images) to existing pages.
- Update properties on existing pages.
- Read page content as Markdown for retrieval-style workflows.
Setup
Install the Notion MCP server
Integrations → Discover → Notion → Install. Server runs locally and authenticates to your workspace via OAuth.
Share the right pages or databases
In Notion: open the page/database you want Actionist to touch, Share → Invite, and add the Actionist integration. Without this, the API can’t see the database.
Common workflows
- Daily Slack digest → Notion page — every morning, write yesterday’s Slack DM summary to a new page in a “Daily digests” database.
- Linear → Notion sync — when a Linear issue closes, append a row to a “Shipped” database with the title, owner, and a 1-sentence summary.
- PDF → Notion — drag a PDF into chat, ask Actionist to extract the key facts as a new Notion page with structured properties.
- Notion as memory — point your research agent’s Files folder at a Notion DB; it retrieves from there when answering questions.
Limits & gotchas
- Database IDs are 32-character UUIDs without dashes. Get them from the Notion URL after the workspace slug.
- Rich text is chunked. Pages with >100 blocks paginate — your read action must follow
next_cursorto get everything. - Notion’s API doesn’t expose every block type. Synced blocks, embeds, and unfurled links return as opaque references.
- Rate limits are 3 requests per second per integration. Long backfills need a sleep.