Get the Shake Shack menu. Can return all categories or a specific category.
AI agents call get_menu to retrieve information from Mcp Shakeshack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays menu information from Shake Shack's database. It performs no data modification, deletion, execution of external commands, or financial transactions. The only risk is potential information disclosure if sensitive menu data exists, but menu information is typically public-facing. This is a straightforward Read operation with minimal security impact.
From the tool's definition Tool name 'get_menu' and description 'Get the Shake Shack menu' indicate retrieval of menu data without modification. The capability to 'return all categories or a specific category' confirms query/filter behavior with no side effects.
Attacks that exploit this kind of access
Get the Shake Shack menu. Can return all categories or a specific category. It is categorised as a Read tool in the Mcp Shakeshack MCP Server, which means it retrieves data without modifying state.
Register the Mcp Shakeshack MCP server in PolicyLayer and add a rule for get_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 Shakeshack. Nothing to install.
get_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 get_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 get_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.
get_menu is provided by the Mcp Shakeshack MCP server (markswendsen-code/mcp-shakeshack). 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 →