AI agents call ms_calendar to retrieve information from M365 MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves calendar information from Microsoft 365, which is a read-only operation with no side effects. However, calendar data can contain sensitive information (meeting details, attendees, times, personal scheduling patterns), warranting medium severity due to potential privacy/confidentiality impact if accessed by unauthorized agents. It does not create, modify, delete, or execute operations.
From the tool's definition Tool name is 'ms_calendar' and server description states 'read-only access to...calendar'. The tool description 'Fetch the user' is incomplete/uninformative, but context from the server description clearly indicates calendar data retrieval.
Attacks that exploit this kind of access
Fetch the user. It is categorised as a Read tool in the M365 MCP MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for ms_calendar: 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 MCP. Nothing to install.
ms_calendar 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 ms_calendar 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 ms_calendar. 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.
ms_calendar is provided by the M365 MCP server (stumason/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 →