Get cone of uncertainty and forecast points for a specific storm
AI agents call get_storm_cone to retrieve information from Hurricane Tracker MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns meteorological forecast data without creating, modifying, deleting, or executing any actions. It has no side effects and presents no risk of unintended consequences if called with any storm identifier. The worst outcome of misuse would be retrieving irrelevant forecast data, which is harmless.
From the tool's definition Tool retrieves forecast cone data and track points for a specific storm. The description uses 'Get' indicating data retrieval with no modification capability.
Attacks that exploit this kind of access
Get cone of uncertainty and forecast points for a specific storm. It is categorised as a Read tool in the Hurricane Tracker MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hurricane Tracker MCP Server MCP server in PolicyLayer and add a rule for get_storm_cone: 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 Hurricane Tracker MCP Server. Nothing to install.
get_storm_cone 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_storm_cone 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_storm_cone. 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_storm_cone is provided by the Hurricane Tracker MCP Server MCP server (kumaran-is/hurricane-tracker-mcp). 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 →