Respond to event invitation (accept, decline, tentativelyAccept)
AI agents use respond_event to create or update resources in Microsoft MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft MCP environment.
This tool sends a response to a calendar event invitation, which creates or modifies state (RSVP status) in the calendar system. It is reversible (you can change your response) and does not delete data, execute code, or involve financial transactions. The blast radius is medium since misuse could accept/decline meetings on behalf of a user without consent.
From the tool's definition Respond to event invitation (accept, decline, tentativelyAccept)
Attacks that exploit this kind of access
Respond to event invitation (accept, decline, tentativelyAccept). It is categorised as a Write tool in the Microsoft MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft MCP server in PolicyLayer and add a rule for 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 Microsoft MCP. Nothing to install.
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 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 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.
respond_event is provided by the Microsoft MCP server (purva-kashyap/microsoft-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 →