READ-ONLY: Retrieve a restaurant's cancellation policy from TableAll. This tool ONLY READS policy data — it does NOT cancel any reservation, modify any data, or perform any action. Safe to call repeatedly. WHEN TO USE — call this tool whenever ANY of the following is true: - The user asks about t...
Part of the Mcp server.
Free to start. No card required.
AI agents call get_cancellation_policies 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_cancellation_policies 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_cancellation_policies": {}
}
}See the full Mcp policy for all 11 tools.
These attack patterns abuse exactly the kind of access get_cancellation_policies 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.
READ-ONLY: Retrieve a restaurant's cancellation policy from TableAll. This tool ONLY READS policy data — it does NOT cancel any reservation, modify any data, or perform any action. Safe to call repeatedly. WHEN TO USE — call this tool whenever ANY of the following is true: - The user asks about the "cancellation policy", "cancellation terms", "refund policy", "no-show fee", "what happens if I cancel", or similar phrasing. - You are about to call create_reservation or create_reservation_request (always show the policy first). - The user is comparing restaurants and policy is a factor. DO NOT try to derive cancellation policy from other tools. - get_restaurant_details returns booking_rules and booking_tips, but these are about WHEN bookings open and how to book — NOT about cancellation. They are NOT a substitute for this tool. - If you have not called get_cancellation_policies for the requested restaurant, you DO NOT have policy information for it. Call this tool. DISPLAY RULES (MUST follow): - Always include the booking fee notice: "Note: The booking fee is non-refundable regardless of cancellation timing." (NEVER skip this.) - For reservation requests, explain that the policy applies AFTER the request is confirmed by the restaurant. Returns: - cancel_policies: array of { days_before, penalty_percentage, description } - policy_type: identifier of the ruleset - message: pre-formatted summary - booking_fee_note: MUST be displayed - important_note: clarifies when the policy takes effect. 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_cancellation_policies: 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_cancellation_policies 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_cancellation_policies 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_cancellation_policies. 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_cancellation_policies 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.