Check if you
AI agents call auth-status to retrieve information from Microsoft Todo Safe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
An auth-status check is a read-only operation that queries the current authentication state. It has no side effects, cannot modify data, and poses minimal risk if misused by an AI agent—it would simply return authentication information already accessible to the agent.
From the tool's definition Tool name 'auth-status' and description 'Check if you' (incomplete but implies status check) indicate a query operation that retrieves authentication state without modifying data or triggering external actions.
Attacks that exploit this kind of access
Check if you. It is categorised as a Read tool in the Microsoft Todo Safe MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Todo Safe MCP server in PolicyLayer and add a rule for auth-status: 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 Todo Safe. Nothing to install.
auth-status 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 auth-status 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 auth-status. 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.
auth-status is provided by the Microsoft Todo Safe MCP server (saenai/microsoft-todo-safe-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 →