Get detailed information about a specific hotel from Google Hotels via SerpAPI. Use this after search_hotels to get full details for a specific property. Pass both the original search query and the property_token from a search result. Returns: Complete hotel info including all booking prices from...
AI agents call get_hotel_details 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 hotel data from a third-party service (Google Hotels via SerpAPI) and returns structured information to the user. There are no state changes, no code execution, no financial transactions, and no destructive operations. The worst-case misuse scenario (an AI agent fetching irrelevant hotel details repeatedly) has minimal blast radius. The tool is a simple data query.
From the tool's definition Tool description states it 'Get[s] detailed information' and 'Returns: Complete hotel info including all booking prices...review sentiment breakdown...amenity list' — purely informational retrieval with no modification, deletion, or execution of external…
Attacks that exploit this kind of access
Get detailed information about a specific hotel from Google Hotels via SerpAPI. Use this after search_hotels to get full details for a specific property. Pass both the original search query and the property_token from a search result. Returns: Complete hotel info including all booking prices from different sources, review sentiment breakdown (positive/negative/neutral by category like cleanliness, location, service), full amenity list, check-in/out times, nearby places with travel times, and GPS coordinates. 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 get_hotel_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 Langfuse Observability. Nothing to install.
get_hotel_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_hotel_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_hotel_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_hotel_details 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 →