Get the FULL detailed profile of one specific restaurant (untrimmed description, booking_rules, booking_tips, address, operating_hours, seating, etc.). WHEN TO USE — call this tool whenever: - The user names a specific restaurant and asks "tell me about", "what's", "details about", "show me", "教え...
Part of the Mcp server.
Free to start. No card required.
AI agents call get_restaurant_details 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_details 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_details": {}
}
}See the full Mcp policy for all 11 tools.
These attack patterns abuse exactly the kind of access get_restaurant_details 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 FULL detailed profile of one specific restaurant (untrimmed description, booking_rules, booking_tips, address, operating_hours, seating, etc.). WHEN TO USE — call this tool whenever: - The user names a specific restaurant and asks "tell me about", "what's", "details about", "show me", "教えて", "について" (e.g., "Tell me about Sushisho Saito"). - The user is comparing specific restaurants and wants more than the short list info from search_restaurants. - You already have a restaurant_id (from search_restaurants) and need the full description / booking rules / seating that search_restaurants does NOT return. DO NOT rely on the trimmed description from search_restaurants when the user is asking about ONE specific restaurant — call this tool to get the full profile. WHAT THIS TOOL DOES NOT RETURN: - This tool does NOT return menu items / courses / their prices. For menu/courses, call get_restaurant_menu. - This tool does NOT return cancellation policy. For cancellation policy, call get_cancellation_policies. - This tool does NOT return real-time availability. For availability, call check_availability. PRICE DISPLAY: - When showing the price, copy starting_price_display as-is (e.g., "¥65,000〜"). The ¥8,000 Booking Fee is already included.. 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_details: 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_details 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_details 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_details. 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_details 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.