AI agents call verify-login to retrieve information from Ms 365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query operation to determine whether the user is currently authenticated. It has no side effects, creates no resources, executes no code, and makes no modifications. This is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'verify-login' and description states 'Check current Microsoft authentication status' — this retrieves authentication state information without modifying or executing anything.
Attacks that exploit this kind of access
Check current Microsoft authentication status. It is categorised as a Read tool in the Ms 365 MCP Server, which means it retrieves data without modifying state.
Register the Ms 365 MCP server in PolicyLayer and add a rule for verify-login: 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 Ms 365. Nothing to install.
verify-login 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 verify-login 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 verify-login. 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.
verify-login is provided by the Ms 365 MCP server (@softeria/ms-365-mcp-server). 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 →