Get Hopper
AI agents call get_price_forecast to retrieve information from Hopper MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Price forecasts are read-only queries that retrieve data with no side effects. While the broader server enables financial actions (book_flight, book_hotel are Financial/Write), this specific tool simply queries forecast data, making it a Read operation with low risk.
From the tool's definition Tool name 'get_price_forecast' and context indicate this retrieves forecasting data from Hopper without modifying state. The description is truncated ('Get Hopper') but the sibling tools (book_flight, book_hotel, set_price_alert) clarify the server's scope.
Attacks that exploit this kind of access
Get Hopper. It is categorised as a Read tool in the Hopper MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hopper MCP Server MCP server in PolicyLayer and add a rule for get_price_forecast: 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 Hopper MCP Server. Nothing to install.
get_price_forecast 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_price_forecast 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_price_forecast. 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_price_forecast is provided by the Hopper MCP Server MCP server (markswendsen-code/mcp-hopper). 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 →