Search the Starbucks menu by name, category, or dietary preferences. Returns matching drinks and food items with prices and calories.
AI agents call search_menu to retrieve information from Mcp Starbucks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves menu information without creating, modifying, deleting, or executing any operations. It is a pure read operation that provides informational data (menu items, prices, calories) to the user. No financial transactions, orders, or destructive actions are involved. The blast radius of misuse is minimal—an agent could only access publicly available menu information.
From the tool's definition Tool description states it 'Search[es] the Starbucks menu by name, category, or dietary preferences. Returns matching drinks and food items with prices and calories.' The verb 'search' and 'returns' indicate retrieval of menu data with no modification or side…
Attacks that exploit this kind of access
Search the Starbucks menu by name, category, or dietary preferences. Returns matching drinks and food items with prices and calories. It is categorised as a Read tool in the Mcp Starbucks MCP Server, which means it retrieves data without modifying state.
Register the Mcp Starbucks MCP server in PolicyLayer and add a rule for search_menu: 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.
search_menu 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 search_menu 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 search_menu. 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.
search_menu 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 →