Notion Markdown MCP server

This MCP server provides seamless navigation of your entire Notion workspace, converting Notion pages into markdown notes that can be searched and retrieved based on graph distance, considering parent-child and reference relationships.

Getting Started

Prerequisites

Before installing the Notion-Texonom MCP server, you'll need:

• Node.js installed on your system
• A Notion workspace
• The ID of your root Notion page

Installation

1. Install the package using npm:

npm install notion-texonom

Or with pnpm:

pnpm install notion-texonom

2. Build the project:

pnpm build

Configuration

The server requires minimal configuration:

• Set the ROOT_PAGE environment variable to your Notion root page ID.

You don't need a Notion API token, as the system works with just the root page identifier.

Setting Up with Claude Desktop

To integrate with Claude Desktop:

On MacOS

Edit the config file at: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows

Edit the config file at: %APPDATA%/Claude/claude_desktop_config.json

Add this configuration:

{
  "mcpServers": {
    "notion-texonom": {
      "command": "node",
      "args": [
        "/path/to/mcp/build/index.js"
      ],
      "env": {
        "ROOT_PAGE": "your-notion-root-page-id"
      }
    }
  }
}

Make sure to replace:

• /path/to/mcp/build/index.js with the actual path to the built index.js file
• your-notion-root-page-id with your actual Notion root page ID

Using the MCP Server

Once configured, you can interact with your Notion workspace through:

Resources

• Access all your Notion pages as markdown notes via note:// URIs with UUID slugs
• Each note includes title, description, and markdown-formatted content

Tools

Searching Notes

Use the search_notes tool to find relevant Notion pages:

Input: Your search query text
Output: Markdown content of matching notes

Prompts

The server provides several built-in prompts to help you work with your Notion content:

• summarize_note: Generate a summary of a specific note
• suggest_refactor: Get suggestions for structural improvements
• suggest_fix: Identify potential issues that need fixing
• suggest_enhance: Receive recommendations to enhance your note

Each prompt takes a Notion page URI as input and returns structured improvement suggestions.

Remote Deployment

For shared usage, you can deploy the server remotely using SSEServerTransport:

npx -y supergateway --port 8000 --stdio "npx -y @modelcontextprotocol/server-filesystem /your/folder/path"

Replace /your/folder/path with the appropriate directory path.

Troubleshooting

If you encounter issues, you can run the MCP Inspector for debugging:

pnpm inspector

This provides a browser-based interface for inspecting the server communication.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.