AI agents call ms_profile 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 user profile information without side effects. The action is non-destructive and limited to fetching existing data. Severity is low because profile information is typically less sensitive than email or financial data, though confidence is high based on explicit read-only positioning in the server description.
From the tool's definition Tool name 'ms_profile' and description 'Fetch the user' indicate data retrieval with no modification. Server description explicitly states 'read-only access to profile', confirming this is a query operation.
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_profile: 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_profile 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_profile 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_profile. 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_profile 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 →