Back to MCP Catalog

Notion Integration MCP Server

Knowledge & MemoryTypeScript
Seamless integration with Notion workspaces for LLMs
Available Tools

search_pages

Search for pages in your Notion workspace

query

read_page

Read the content of a specific Notion page

pageId

create_page

Create a new page in Notion with markdown content

parentPageIdtitlecontentproperties

update_page

Update the content of an existing Notion page

pageIdcontenttype

create_database

Create a new database in Notion

parentPageIdtitleproperties

query_database

Query a Notion database with filters and sorting options

databaseIdfiltersort

The Notion Integration MCP provides a comprehensive bridge between language models and your Notion workspace. It enables AI assistants to search, read, create, and update pages and databases in Notion through a standardized set of tools. With support for rich markdown content, database operations, and page management, this integration allows language models to become powerful collaborators in your Notion-based workflows. The server handles complex operations like nested content structures, property management, and formatted outputs to ensure a smooth experience.

Overview

The Notion Integration MCP server enables language models to interact with your Notion workspace through a standardized interface. This allows AI assistants to search, read, create, and update content in your Notion pages and databases.

Installation

Prerequisites

Before setting up the Notion Integration MCP, ensure you have:

  1. Node.js v16 or higher installed
  2. A Notion API key
  3. An MCP-compatible client (such as Claude Desktop)

Setup Steps

  1. Clone the repository:
git clone https://github.com/v-3/notion-server.git
cd notion-server
  1. Install dependencies:
npm install
  1. Build the server:
npm run build
  1. Configure your environment by creating a .env file with your Notion API key:
NOTION_API_KEY=your_notion_api_key_here

Notion API Configuration

To use this MCP, you'll need to set up a Notion integration:

  1. Visit Notion Integrations
  2. Click "New integration" and give it a name
  3. Configure the following permissions:
    • Content capabilities: Read, Update, Insert
    • Comment capabilities: Read, Create
    • User information: Read
  4. Copy the API key for use with the MCP server

After creating your integration, you need to connect it to your Notion pages:

  1. Open each Notion page you want to access
  2. Click the "..." menu in the top-right corner
  3. Select "Connections" and add your integration
  4. Repeat for all pages you want the MCP to access

Configuration

To configure the MCP with Claude Desktop, update your Claude Desktop configuration file:

{
    "mcpServers": {
        "notion": {
            "command": "node",
            "args": ["/absolute/path/to/notion-server/build/index.js"],
            "env": {
                "NOTION_API_KEY": "your_notion_api_key_here"
            }
        }
    }
}

After updating the configuration, restart Claude Desktop to apply the changes.

Usage

Once configured, the MCP provides tools for interacting with Notion. You can use these tools to:

  • Search for pages in your workspace
  • Read page content
  • Create new pages with rich markdown content
  • Update existing pages
  • Work with databases (create, query, update)
  • Add and retrieve comments

The MCP handles the conversion between markdown and Notion's block structure, allowing for rich content creation including headings, code blocks, todo items, blockquotes, and more.

Troubleshooting

If you encounter issues:

  1. Verify your Notion API key is correct
  2. Ensure your integration has been granted access to the pages you're trying to access
  3. Check that the path to the server in your configuration is correct
  4. Look for error messages in the Claude Desktop logs

For more detailed information or to contribute to the project, visit the GitHub repository.

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.