name: notion description: How to work with Notion via MCP. Use when the user wants to read, search, create, or update Notion pages, databases, or workspace content.
Finding and reading
Search by name or topic: notion-search → notion-fetch
Tasks / filtered queries: notion-search → notion-query-database-view or notion-query-data-sources
With Notion AI, notion-search also covers connected Slack / Drive / Jira
Creating content
New page: ask where to save if unspecified, then notion-create-pages
Database entry: notion-fetch the DB first to get exact property names → notion-create-pages
New database: notion-create-database → notion-create-view for board/calendar/timeline
Updating content
Property change: notion-search → notion-update-page
Targeted edit: notion-fetch → notion-update-page with update_content
Full rewrite: notion-update-page with replace_content — confirm first
Comment: notion-create-comment; read existing ones with notion-get-comments
DB schema change: notion-update-data-source
Organizing
Move page: notion-search both ends → notion-move-pages
Duplicate: notion-duplicate-page
Add view: notion-create-view; edit view: notion-update-view
Summarizing
Status report: notion-search → notion-query-data-sources → aggregate and present
Overdue tasks: query task DB with past due date + status not Done
By assignee: query task DB, group by person property
People
Workspace members: notion-get-users; teamspaces: notion-get-teams
Best Practices
- Search before fetch — semantic search usually resolves by name in one call
- Fetch DB schema before inserting — property names must match exactly
- Prefer
update_contentoverreplace_contentto avoid overwriting others' work - Ask where to save — pages without a parent go to private workspace
- Confirm before moving pages, bulk edits, or full rewrites
- Search rate limit is 30 req/min — avoid tight loops