View past Hilton stays, including hotel names, dates, points earned, and total nights. Requires being logged in.
AI agents call get_stay_history 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 existing stay history data without creating, modifying, deleting, or executing external operations. The action is purely informational and has no side effects on the Hilton system or user account beyond data disclosure.
From the tool's definition Tool name 'get_stay_history' and description 'View past Hilton stays, including hotel names, dates, points earned, and total nights' indicate read-only retrieval of historical data with no modification or irreversible action.
Attacks that exploit this kind of access
View past Hilton stays, including hotel names, dates, points earned, and total nights. Requires being logged in. 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 get_stay_history: 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.
get_stay_history 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_stay_history 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_stay_history. 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_stay_history 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 →