AI agents use calendar_respond_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.
Responding to calendar invitations creates or updates RSVP records that affect scheduling visibility for other attendees. This is reversible (can change response later), so it's Write rather than Execute or Destructive. Severity is medium because incorrect responses could disrupt meeting coordination but don't cause data loss or financial impact.
From the tool's definition Tool name contains 'respond' for calendar events; based on M365 calendar patterns, this modifies event attendance status (accept/decline/tentative), which changes shared calendar state.
Attacks that exploit this kind of access
calendar_respond_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_respond_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_respond_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_respond_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_respond_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_respond_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 →