Search for hotels using Google Hotels via SerpAPI. Returns a list of hotels with prices, ratings, reviews, amenities, and booking information for a given location and date range. Pagination: The response includes a next_page_token. To get more results, call search_hotels again with the same param...
AI agents call search_hotels to retrieve information from Langfuse Observability 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 information from an external API (Google Hotels via SerpAPI). It performs no writes, deletions, code execution, or financial transactions. The pagination, sorting, and filtering capabilities are all read-only operations that do not modify any state. The tool simply returns data to the user without making changes to any system or committing the user to any action.
From the tool's definition Tool description states it 'Search for hotels' and 'Returns a list of hotels with prices, ratings, reviews, amenities, and booking information.' The operations described are query-only: pagination via next_page_token, sorting results, and filtering—all read…
Attacks that exploit this kind of access
Search for hotels using Google Hotels via SerpAPI. Returns a list of hotels with prices, ratings, reviews, amenities, and booking information for a given location and date range. Pagination: The response includes a next_page_token. To get more results, call search_hotels again with the same parameters plus the next_page_token value. Sorting: Use sort_by to order results: 3 = lowest price, 8 = highest rating, 13 = most reviewed. Filtering: Narrow results by price range, star rating, minimum review rating, free cancellation, and more. Use get_hotel_details with a property_token from the results to get detailed pricing, reviews breakdown, and full amenity lists for a specific hotel. It is categorised as a Read tool in the Langfuse Observability MCP Server, which means it retrieves data without modifying state.
Register the Langfuse Observability 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 Langfuse Observability. 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 Langfuse Observability MCP server (langfuse-observability-mcp-server). 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 →