Access and Manage OneNote Data
MCP server connector that exposes Microsoft OneNote integration tools to AI clients, enabling programmatic access to notebooks, sections, and pages through the
Why it matters
Integrate AI assistants with Microsoft OneNote, enabling them to read and write notebook content. This asset facilitates structured data access for AI-driven tasks.
Outcomes
What it gets done
Read OneNote notebooks, sections, and pages.
Create new OneNote content (notebooks, sections, pages).
Convert HTML content to text for AI processing.
Authenticate with Microsoft Graph API for secure access.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-onenote | bash Capabilities
Tools your agent gets
Read content from Microsoft OneNote notebooks, sections, or pages with optional metadata and content.
Create new content in Microsoft OneNote, including pages, sections, or notebooks with HTML content.
Overview
OneNote MCP Server
What it does
This MCP server connects AI clients to Microsoft OneNote through the Model Context Protocol. It exposes OneNote operations-retrieving notebooks, creating sections, reading and updating page content-as callable tools. Any MCP-compatible AI assistant can invoke these tools to interact with OneNote programmatically.
How it connects
Use this connector when you need AI agents to access or modify OneNote content during conversations or workflows. Ideal for scenarios where an assistant must query meeting notes, append research to existing pages, or organize information across notebooks and sections without manual intervention.
Source README
An MCP server that provides AI assistants with access to Microsoft OneNote, enabling reading and writing data to OneNote notebooks, sections, and pages using the Microsoft Graph API.
Installation
From Source Code
git clone [repository]
npm install
npm run build
npm start
Docker
mkdir -p data
docker build -t onenote-mcp-server .
docker run -d --name onenote-mcp-server -e CLIENT_ID=your-client-id -v $(pwd)/data:/app/dist onenote-mcp-server
Configuration
Claude Desktop
Set the server directory to your cloned repository
Set the command to: npm run build && npm start
Add environment variable:
- Name: CLIENT_ID
- Value: [Your Microsoft Azure Application Client ID]
Available Tools
| Tool | Description |
|---|---|
onenote-read |
Reading content from Microsoft OneNote notebooks, sections, or pages with optional metadata and content... |
onenote-create |
Creating new content in Microsoft OneNote, including pages, sections, or notebooks with HTML content... |
Features
- Read notebooks, sections, and pages from OneNote
- Create new notebooks, sections, and pages in OneNote
- Convert HTML content to text for improved RAG processing
- Authentication via device code flow with Microsoft Graph API
- Token caching for persistent authentication
- Docker support for containerized deployment
Environment Variables
Required
CLIENT_ID- Your Microsoft Azure application Client ID for authentication## Notes
Requires a Microsoft Azure account with a registered application and API permissions (Notes.Read, Notes.ReadWrite). Uses device code flow authentication-on first run, a code is generated and saved to device-code.txt, which must be entered at the provided URL. Tokens are cached in token-cache.json for future use.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.