AI agents call get_event_types to retrieve information from Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists metadata about supported disaster event types—a read-only query with no side effects. The operation does not modify, delete, execute, or trigger external actions. It is purely informational, similar to retrieving a schema or enumeration. The blast radius of misuse is minimal, as it only returns reference information that would typically be public or widely available.
From the tool's definition Tool name 'get_event_types' and description 'Get list of all supported disaster event types with their descriptions' indicate a simple retrieval operation that returns static reference data about event types.
Attacks that exploit this kind of access
Get list of all supported disaster event types with their descriptions. It is categorised as a Read tool in the Api MCP Server, which means it retrieves data without modifying state.
Register the Api MCP server in PolicyLayer and add a rule for get_event_types: 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 Api. Nothing to install.
get_event_types 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_event_types 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_event_types. 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_event_types is provided by the Api MCP server (https://api.gdacs.org/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 →