Search for Hilton hotels by location and dates. Returns hotel names, brands, ratings, prices, and points rates.
AI agents call search_hotels to retrieve information from Mcp Hilton without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries hotel availability and pricing data without creating, modifying, deleting, or executing operations. It poses minimal risk even if misused by an AI agent, as the worst outcome would be performing unwanted searches on public hotel inventory.
From the tool's definition Tool searches for hotels and returns hotel names, brands, ratings, prices, and points rates—a pure information retrieval operation with no side effects or modifications.
Attacks that exploit this kind of access
Search for Hilton hotels by location and dates. Returns hotel names, brands, ratings, prices, and points rates. It is categorised as a Read tool in the Mcp Hilton MCP Server, which means it retrieves data without modifying state.
Register the Mcp Hilton MCP server in PolicyLayer and add a rule for search_hotels: 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 Hilton. Nothing to install.
search_hotels 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_hotels 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_hotels. 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_hotels is provided by the Mcp Hilton MCP server (markswendsen-code/mcp-hilton). 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 →