Back to MCP Catalog

Notion Integration MCP Server

Knowledge & MemoryTypeScript
Interact with Notion workspaces through LLMs
Available Tools

notion_append_block_children

Append child blocks to a parent block in Notion

block_idchildrenformat

notion_retrieve_block

Retrieve information about a specific block in Notion

block_idformat

notion_retrieve_block_children

Retrieve the children of a specific block in Notion

block_idstart_cursorpage_sizeformat

notion_delete_block

Delete a specific block in Notion

block_idformat

notion_retrieve_page

Retrieve information about a specific page in Notion

page_idformat

notion_update_page_properties

Update properties of a page in Notion

page_idpropertiesformat

notion_create_page

Create a new page in Notion

parentpropertieschildreniconcoverformat

notion_update_block

Update a block in Notion

block_idblockformat

notion_query_database

Query a database in Notion

database_idfiltersortsstart_cursorpage_sizeformat

notion_retrieve_database

Retrieve information about a database in Notion

database_idformat

notion_update_database

Update a database in Notion

database_idtitledescriptionpropertiesformat

notion_create_database

Create a new database in Notion

parenttitlepropertiesformat

notion_search

Search for pages and databases in Notion

querysortfilterstart_cursorpage_sizeformat

notion_list_all_users

List all users in a Notion workspace

start_cursorpage_sizeformat

notion_retrieve_user

Retrieve information about a specific user in Notion

user_idformat

notion_retrieve_bot_user

Retrieve information about the bot user in Notion

format

notion_create_comment

Create a comment in Notion

parentrich_textdiscussion_idformat

notion_retrieve_comments

Retrieve comments from a page or block in Notion

block_idstart_cursorpage_sizeformat

The Notion Integration MCP enables large language models to interact directly with Notion workspaces through the Notion API. It provides comprehensive access to Notion's functionality, allowing LLMs to retrieve, create, update, and delete content across pages, databases, and blocks. This integration features an experimental Markdown conversion capability that significantly reduces context size when communicating with LLMs. By transforming Notion's complex JSON structures into readable Markdown, it optimizes token usage and makes interactions more efficient while maintaining the ability to work with the original data structure when needed.

Overview

The Notion Integration MCP serves as a bridge between large language models and Notion workspaces, enabling AI assistants to interact with your Notion content. This integration supports a wide range of operations including reading and writing pages, querying databases, managing blocks, and handling comments.

Prerequisites

Before setting up the Notion Integration MCP, you'll need:

  1. A Notion account with access to the workspace you want to integrate
  2. Permission to create integrations in your Notion workspace

Installation

To install and configure the Notion Integration MCP, follow these steps:

Step 1: Create a Notion Integration

  1. Visit the Notion Integrations page
  2. Click "New Integration"
  3. Name your integration (e.g., "Claude Assistant")
  4. Select the appropriate capabilities:
    • "Read content" (required)
    • "Update content" (if you want to allow writing)
    • "Insert content" (if you want to allow creating new content)
  5. Complete the integration creation process

Step 2: Get Your Integration Token

After creating the integration, you'll be provided with an "Internal Integration Token." This is your NOTION_API_TOKEN that will be used to authenticate the MCP.

Step 3: Add the Integration to Your Workspace

For each page or database you want the AI to access:

  1. Open the page/database in Notion
  2. Click the "•••" menu in the top right corner
  3. Select "Connections"
  4. Find and select your newly created integration
  5. Click "Confirm" to grant access

Step 4: Configure Your AI Client

Add the following configuration to your AI client's configuration file (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "notion": {
      "command": "npx",
      "args": ["-y", "@suekou/mcp-notion-server"],
      "env": {
        "NOTION_API_TOKEN": "your-integration-token-here"
      }
    }
  }
}

Advanced Configuration

Enabling Markdown Conversion

To reduce token consumption when viewing content, you can enable the experimental Markdown conversion feature:

{
  "mcpServers": {
    "notion": {
      "command": "npx",
      "args": ["-y", "@suekou/mcp-notion-server"],
      "env": {
        "NOTION_API_TOKEN": "your-integration-token-here",
        "NOTION_MARKDOWN_CONVERSION": "true"
      }
    }
  }
}

With this feature enabled, you can control the format on a per-request basis:

  • Use "format": "markdown" for better readability when only viewing content
  • Use "format": "json" when you need to modify the returned content

Limiting Available Tools

If you want to restrict the MCP to only use certain tools (for example, to create a read-only integration), you can specify the enabled tools using the --enabledTools argument:

{
  "mcpServers": {
    "notion": {
      "command": "npx",
      "args": [
        "-y", 
        "@suekou/mcp-notion-server", 
        "--enabledTools=notion_retrieve_block,notion_retrieve_block_children,notion_retrieve_page,notion_query_database,notion_retrieve_database,notion_search"
      ],
      "env": {
        "NOTION_API_TOKEN": "your-integration-token-here"
      }
    }
  }
}

Troubleshooting

If you encounter issues with the Notion Integration MCP:

  1. Permission Errors: Ensure your integration has the necessary permissions and is invited to all relevant pages/databases.

  2. Authentication Errors: Verify your NOTION_API_TOKEN is correct and properly configured in your client settings.

  3. Content Not Appearing: Check that the integration has been explicitly added to each page or database you want to access.

  4. Editing Issues with Markdown Conversion: When using Markdown conversion, switch to JSON format ("format": "json") when you need to edit content to preserve the original structure.

Related MCPs

Knowledge Graph Memory
Knowledge & MemoryTypeScript

A persistent memory system using a local knowledge graph

MemoryMesh
Knowledge & MemoryTypeScript

A knowledge graph server for structured memory persistence in AI models

Cognee
Knowledge & MemoryPython

Knowledge management and retrieval system with code graph capabilities

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.