AI agents use calendar_create_event to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.
Creating calendar events is a reversible write operation that modifies user calendar data. While not destructive (events can be deleted/edited), it creates new data structures and could impact scheduling if misused by an AI agent (e.g., spam events, fake meetings). Medium severity reflects the data modification impact and potential for disruption, but the reversible nature prevents higher classification.
From the tool's definition Tool name 'calendar_create_event' indicates creation of calendar events in Microsoft 365 Calendar service. The server description confirms it manages Calendar through natural language commands.
Attacks that exploit this kind of access
calendar_create_event. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M365 MCP server in PolicyLayer and add a rule for calendar_create_event: 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 M365. Nothing to install.
calendar_create_event 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 calendar_create_event 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 calendar_create_event. 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.
calendar_create_event is provided by the M365 MCP server (robin-collins/m365-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 →