OneNote MCP. Search and organize your notes like a database.
OneNote MCP connects your AI agent directly to Microsoft OneNote, treating your entire collection of notes like a single digital brain. Your agent can instantly search across thousands of pages, map complex notebook structures, and pull out raw text content without you ever leaving the chat interface.
Give Claude and any AI agent real-world access
It searches across all your notebooks and pages for specific keywords or phrases, regardless of how deeply they are filed.
It pulls the plain written text from any single page, bypassing OneNote's complex formatting so you get clean data.
It generates a map of your entire organizational logic, listing notebooks, section groups, and sections in order.
You can send text blocks or summaries directly into an existing notebook section using the chat interface.
Ask an AI about this
Waiting for input…
What AI agents can do with OneNote with 7 Tools
These tools give your agent the ability to navigate every part of OneNote's structure—from listing main containers to pulling raw content from individual pages.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using OneNote MCPList Notebooks
Lists all primary notebooks available in your OneNote structure.
Get Notebook
Retrieves detailed information about a specific, named notebook container.
List Sections
Finds all sections inside a given notebook, helping you narrow down the content...
List Pages
Lists metadata (titles and IDs) for every page within a specific section.
Get Page Content
Extracts the actual written text content from one chosen page.
Search Pages
Searches for a keyword or phrase across all your notebooks globally, instantly.
List Section Groups
Maps out multi-layered organizational groupings, useful for textbook or curriculum structures.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with OneNote, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by OneNote. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS CLOUD
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
The Struggle with Digital Archives
Right now, finding a single piece of information means opening OneNote. You navigate through notebook groups and sections until you hit the right folder, then click into multiple pages. If the note is old or buried deep in a rarely used section, you waste ten minutes clicking around just to find the correct location.
With this MCP, your agent handles the navigation entirely. Instead of manual clicks and searching through nested folders, you simply ask for the information using natural language. It finds the page ID, extracts the content, and gives you clean text instantly. You get context, not a folder structure.
Accessing OneNote Content with `get_page_content`
The biggest manual step that goes away is the copy-paste headache. When you read content in one of your notes, it often comes wrapped in proprietary formatting or complex HTML tags, making plain text extraction a pain.
Now, when you use the agent to fetch content via `get_page_content`, it delivers the pure written material. You get actionable data that's ready for immediate analysis, without needing cleanup.
What OneNote MCP does for your AI
Imagine having every meeting note, research citation, and brainstorm session stored in Microsoft OneNote suddenly accessible to your AI client. This MCP lets your agent dive into your personal or corporate notebooks like a librarian finding one specific card in a vast archive. Instead of manually clicking through nested sections and pages, you simply ask the question.
Your agent then finds it—it searches global page content for keywords across all active notes, pulls out only the raw text from the relevant section, and even maps the entire structural hierarchy so you know exactly where everything lives.
It's a huge time saver. You can get your AI client to append quick summaries or thoughts directly into an existing note right from our chat conversation. This capability turns OneNote from just storage into an active knowledge base. With Vinkius, this MCP gives your agent the deep context it needs to work with complex documents instantly.
019d75e5-a62b-735f-9923-e0db8499676e How to set up OneNote MCP
The bottom line is that your AI agent treats your private OneNote files like a database it can query in real time.
First, enable this local MCP integration and provide your AI client with a Microsoft Graph Access Token scoped to OneNote.
Next, you simply write natural language commands into your agent, asking it to find specific information or map out your notes' structure.
The AI uses the connected tools to search the content, extract the text, or append new material, presenting only the actionable result back to you.
Who uses OneNote MCP
Anyone whose job involves managing or retrieving large volumes of unstructured text—researchers, project leads, and corporate knowledge workers. This is for people tired of wasting hours clicking through folder structures just to find one sentence.
Pulling specific meeting decisions or action items from deep archive notes across multiple team members' notebooks.
Traversing massive personal knowledge bases to find obscure citations, dates, or quotes needed for a paper.
Reviewing lengthy draft documents and appending brief, contextual summaries or follow-up tasks into the executive planner notes.
Benefits of connecting OneNote MCP
Stop manual searching. Use the search_pages tool to find specific keywords across every notebook instantly, eliminating time spent clicking through folders.
Get clean data without formatting headaches. The get_page_content tool pulls raw text from any page, letting you process content exactly as plain text should be.
Map your entire knowledge base. By using list_notebooks, list_section_groups, and list_sections, your agent builds a complete structural map of your work.
Keep notes current. Use the built-in appending capability to send summaries or quick thoughts directly into an existing section from our chat conversation.
Deep dive into structure. The list_pages tool gives you metadata for all pages in a section, letting you index and reference content without needing to read every page first.
OneNote MCP use cases
Finding the one meeting decision from six months ago
A project lead needs to verify which team member agreed on the new API endpoint. Instead of opening dozens of old meeting notes, they ask their agent to search_pages for 'API endpoint agreement'. The agent instantly finds the correct paragraph across all notebooks and extracts it.
Structuring a large research paper
A researcher has citation notes scattered over years. They use the agent to list_notebooks, then map the structure using list_section_groups. This shows them all related sections, letting them quickly pull citations needed for a bibliography.
Summarizing an executive update
An assistant receives a massive document with notes from three different departments. They ask the agent to read the content and summarize it, using the appending feature to drop the final summary right into the 'Weekly Report' section.
Archiving knowledge for future use
A consultant finishes a major client project and needs to save all key decisions. They instruct the agent to gather notes from specific sections using list_pages first, then ask it to compile and append that clean text into a 'Project Archive' notebook.
OneNote MCP tradeoffs
What to watch out for, and the recommended way to handle each one.
Asking for general context
Writing, 'Tell me about my notes from Q3.' This is too vague; the agent doesn't know which notes you mean or how deep to look.
Be specific. Use a tool like search_pages and ask: 'Search pages for keywords related to 'Q3 marketing budget'. This forces the agent to use its powerful, targeted search capability.'
Assuming data structure
Telling the agent, 'Go find the notes in the finance section.' The agent doesn't know if you mean a section or a group.
First, map the hierarchy. Use list_notebooks to get all containers, then use list_section_groups and list_sections to define your path clearly before asking for content.
Asking for formatted output
Requesting the 'full document with colors and tables.' You only get complex HTML that's hard to use.
Always ask the agent to get_page_content. This forces it to extract the raw, clean text you can actually copy, paste, or process further.
When to use OneNote MCP
Use this MCP if your primary pain point is retrieving specific, stored information from a highly structured source like Microsoft OneNote. You need to know what was written and where it lives—whether that's a citation buried in an old section or a keyword mentioned across ten different notebooks. Don't use this if you need real-time web data (like checking today's stock price) or if your notes are spread across many non-connected services, because this connector only works within the OneNote ecosystem. If you just need to write a simple note, you don't need it; but if you need to find and pull structured context from years of institutional memory, this is exactly what you need.
Frequently asked questions about OneNote MCP
How does OneNote MCP search across my entire notebook? +
The search_pages tool allows the agent to run a global keyword search across all your active notebooks simultaneously. This avoids searching just one section or one page at a time.
Is OneNote MCP suitable for reading images embedded in my notes? +
The primary function is text extraction and searching, so it's best for written content. While the tool can index metadata, getting readable data requires specific tools like get_page_content.
Can I use OneNote MCP to create new notebooks? +
The current scope focuses on reading and structuring existing notes. You must rely on native OneNote features to create brand-new containers; the MCP is for access, not creation.
How do I map out my entire corporate knowledge base using OneNote MCP? +
You combine several tools: use list_notebooks first, then list_section_groups, and finally list_sections. The agent can traverse this structure to give you a complete organizational overview.
What is the difference between list_pages and get_page_content in OneNote MCP? +
list_pages only retrieves metadata, giving you IDs and titles. get_page_content, however, performs the deeper action of retrieving the actual raw text written on that specific page.