Get the menu (course names and their prices) for a specific restaurant. WHEN TO USE — call this tool whenever the user asks about: - "menu", "courses", "what they serve", "メニュー", "コース", "料理" - "pricing", "price for the course", "how much", "値段", "料金" (when paired with a specific restaurant name) ...
Part of the Mcp server.
Free to start. No card required.
AI agents call get_restaurant_menu to retrieve information from Mcp without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_restaurant_menu only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_restaurant_menu": {}
}
}See the full Mcp policy for all 11 tools.
These attack patterns abuse exactly the kind of access get_restaurant_menu gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get the menu (course names and their prices) for a specific restaurant. WHEN TO USE — call this tool whenever the user asks about: - "menu", "courses", "what they serve", "メニュー", "コース", "料理" - "pricing", "price for the course", "how much", "値段", "料金" (when paired with a specific restaurant name) - "show me [restaurant name]'s menu/courses with pricing" Returns an array of menu items, each with course name and price ONLY. STRICT OUTPUT RULES — read carefully: - This tool returns course NAMES and PRICES. It does NOT return dish lists, course composition, number of pieces, ingredients, "what is included", or sample items. - You MUST NOT invent, infer, hallucinate, or supplement any dish-level / item-level breakdown (e.g., "appetizers → nigiri → soup → dessert", "10-15 pieces", "tuna progression"). Even general knowledge about omakase structure is forbidden in your reply. - When the user asks "what's included", "what dishes", "course composition", "details", etc., display ONLY the course name + price from the response, then direct the user to the restaurant page URL (see details_url in the response) for full details.. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for get_restaurant_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. Nothing to install.
get_restaurant_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_restaurant_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_restaurant_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_restaurant_menu is provided by the MCP server (https://mcp.tableall.com/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.