AI agents call calendar_list_calendars to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
List/read operations on calendars are non-destructive and return data without side effects. This is a standard information retrieval action. Low severity because calendar metadata exposure has limited direct impact compared to destructive or financial operations. Confidence slightly reduced due to missing description, but the 'list' verb strongly indicates Read category.
From the tool's definition Tool name 'calendar_list_calendars' indicates a list operation on calendar resources. No description provided, but naming conventions and context as part of M365 calendar management suite suggest data retrieval without modification.
Attacks that exploit this kind of access
calendar_list_calendars. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for calendar_list_calendars: 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_list_calendars is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the calendar_list_calendars 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_list_calendars. 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_list_calendars 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 →