Notion

Notion MCP Connector for Claude

A+

Unified AI interface for your Notion workspace — search pages, query databases, and manage blocks via AI.

17 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Unlock the full potential of your connected workspace by linking Notion to your AI agent. This integration transforms Notion from a static documentation hub into a dynamic, queryable engine for your AI workflows. Your agent can now perform global fuzzy searches to locate misplaced documents, query structured databases to extract tabular data, and even read deep into nested block hierarchies to summarize project specs or meeting notes. Whether you're automating task creation or retrieving team knowledge, your agent acts as an intelligent librarian for your entire Notion domain.

What you can do

  • Global Search — Rapidly find pages and databases across your workspace by title or content using fuzzy text matching.
  • Database Orchestration — Query databases to read structured data rows or fetch the exact schema defining your trackers.
  • Deep Content Reading — Access metadata and dive into nested paragraphs, lists, and images using advanced block retrieval.
  • Record Creation — Programmatically create new pages or insert data rows directly inside specific Notion containers.
  • Identity Mapping — Enumerate all workspace users and bots to accurately map assignee tags to team members.

How it works

  1. Subscribe to this server
  2. Enter your Notion Internal Integration Secret
  3. Start querying your company wiki and project trackers from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Productivity Experts — quickly search the internal wiki, read deep project specs, and append notes to central databases.
  • Software Teams — query central sprint trackers and create new tasks without ever leaving your development environment.
  • Ops Managers — build automated AI reporting flows by safely reading the real-time state of active rows and users.
  • Knowledge Workers — retrieve specific documentation fragments instantly through natural language conversation.
workspace-automationdatabase-querydocument-managementfuzzy-searchblock-management

17 tools expose this connector's capabilities to your AI agent.

append_block_children

Append blocks to page. Supports simple text or full JSON

delete_block

Delete block and its children. Irreversible

get_blocks

Read page content blocks (paragraphs, lists, headings)

get_database

Get database schema (columns, types, options). Call before create_page

query_database

Query database rows. Supports filter/sort as JSON

update_page_properties

Update page properties (status, select, date, etc)

update_page_title

Update page title. Specify property name if not Name

archive_page

Archive page (move to trash)

create_database

Create database inside page

create_page

Create database row. Minimal: title. Advanced: full properties JSON

get_block

Get single block by ID

get_page

Get page metadata (properties, parent, url). Use get_blocks for content

get_user

Get user by ID

list_users

List workspace users and bots. Use to map assignee IDs

search_databases

Search databases by title. Returns database_id needed for query_database

search_pages

Search pages by title. Returns page_id needed for get_page/get_blocks

update_block

Update block content

See how to talk to your AI agent using Notion.

Search my Notion workspace for any pages containing 'Q4 Marketing Strategy'.

I searched your Notion workspace and found the page 'Q4 Marketing Strategy (Final)' with ID `abc-123`. Let me know if you would like me to read the contents of its blocks.

Create a new row in my Project Tasks database marking the title as 'Update API Docs'.

I've successfully created a new active row 'Update API Docs' within the Project Tasks database. The new record has been initialized and is ready for further updates.

List all team members currently registered in my Notion.

Here are the users active within your Notion domain: Jane Doe (`jane@domain.com`), John Smith (`john@domain.com`), and 3 active Bot integrations.

Yes. Your agent can pull the exact schema of your tracker database, retrieve the user UUIDs via `list_users`, and seamlessly insert a new row assigning the task—all within seconds.

Related Connectors