Log out of Starbucks by clearing stored session cookies. Use this to reset authentication state.
AI agents call starbucks_logout to permanently remove resources in Mcp Starbucks — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Logging out irreversibly destroys the current session/authentication tokens. While the user can log back in, the act of clearing session cookies is a one-way destruction of the current auth state — it cannot be undone (the session is terminated). This could disrupt an ongoing workflow, cause loss of cart state, or lock out an AI agent mid-task.
From the tool's definition 'clearing stored session cookies' and 'reset authentication state'
Attacks that exploit this kind of access
Log out of Starbucks by clearing stored session cookies. Use this to reset authentication state. It is categorised as a Destructive tool in the Mcp Starbucks MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Starbucks MCP server in PolicyLayer and add a rule for starbucks_logout: 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 Mcp Starbucks. Nothing to install.
starbucks_logout is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the starbucks_logout 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 starbucks_logout. 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.
starbucks_logout is provided by the Mcp Starbucks MCP server (markswendsen-code/mcp-starbucks). 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 →