Update the content of an existing OneNote page using JSON patch commands. Each patch specifies a target element, an action (append, insert, replace), and content. Before updating, use get-page-content with includeIds=true to get element IDs for targeting.
AI agents use update-page to create or update resources in Onenote — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Onenote environment.
update-page creates or modifies data in a reversible manner (Write category). Severity is medium because: (1) modifications are confined to OneNote pages the authenticated user owns/can access, (2) changes are reversible (can be undone), and (3) no financial impact or irreversible destruction occurs. Confidence is high because the description clearly indicates modification operations on existing content.
From the tool's definition Tool description explicitly states 'Update the content of an existing OneNote page' and accepts 'patch commands' with actions like 'append, insert, replace'. The tool modifies existing data reversibly without permanent deletion.
Attacks that exploit this kind of access
Update the content of an existing OneNote page using JSON patch commands. Each patch specifies a target element, an action (append, insert, replace), and content. Before updating, use get-page-content with includeIds=true to get element IDs for targeting. It is categorised as a Write tool in the Onenote MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Onenote MCP server in PolicyLayer and add a rule for update-page: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Onenote. Nothing to install.
update-page is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-page rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update-page. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update-page is provided by the Onenote MCP server (jacob-hartmann/onenote-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →