// SCAN REPORT

Onenote

12 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

7 can modify or destroy data

5 read-only

12 tools total

Community server · catalogue entry verified 11/06/2026

How to control Onenote ↓

TOOL MAP

Read (5) Write / Execute (5) Destructive / Financial (1)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · Medium clear_token_cache Clearing stored authentication tokens is an irreversible destructive action — once tokens are deleted, the current session/auth state is lost and cannot be undone without re-authenticating. Write · Medium create_notebook Creating a new notebook is a reversible write operation that modifies the user's OneNote data structure. Write · Medium create_page This tool creates new pages in OneNote sections, which modifies the user's notebook by adding reversible content. Write · Medium create_section This tool creates a new organizational unit (section) in OneNote, which is a write operation that modifies the notebook structure.

7 of Onenote's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL ONENOTE

PolicyLayer is an MCP gateway — it sits between your AI agents and Onenote, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_token_cache": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "complete_authentication": {
    "limits": [
      {
        "counter": "complete_authentication_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_authentication": {
    "limits": [
      {
        "counter": "check_authentication_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Onenote — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ONENOTE →

Free to start. No card required.

ALL 12 ONENOTE TOOLS

DESTRUCTIVE 1 tools

Destructive clear_token_cache Clear the stored authentication tokens.

WRITE 5 tools

Write complete_authentication Complete the authentication process after user enters device code. Write create_notebook Create a new OneNote notebook. Write create_page Create a new page in a OneNote section. Write create_section Create a new section in a OneNote notebook. Write update_page_content Update the content of an existing OneNote page.

READ 5 tools

Read check_authentication Check current authentication status and token validity. Read get_page_content Get the content of a specific page. Read list_notebooks List all OneNote notebooks. Read list_pages List pages in a specific section. Read list_sections List sections in a specific notebook.

OTHER 1 tools

Other start_authentication Start the full authentication process.

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Onenote MCP server? +

Yes. The Onenote server exposes 1 destructive tools including clear_token_cache. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Onenote? +

The Onenote server has 5 write tools including complete_authentication, create_notebook, create_page. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Onenote.

How many tools does the Onenote MCP server expose? +

12 tools across 4 categories: Destructive, Execute, Read, Write. 5 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Onenote? +

Register the Onenote MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Onenote tool call.

Deterministic rules across all 12 Onenote tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ONENOTE →

Free to start. No card required.

12 Onenote tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Onenote

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL ONENOTE

// ALL 12 ONENOTE TOOLS

// RELATED SERVERS

// FAQ