Inventory animals on the operator
AI agents call list_animals to retrieve information from ezyVet MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries animal data from the veterinary practice system with no side effects. It is a standard inventory listing operation that falls clearly within the Read category. The low severity reflects minimal risk if misused by an AI agent—the worst outcome would be unauthorized viewing of animal records, not data loss or financial harm.
From the tool's definition Tool name 'list_animals' and description 'Inventory animals on the operator' indicate a query/retrieval operation that retrieves a list of animals without modifying data.
Attacks that exploit this kind of access
Inventory animals on the operator. It is categorised as a Read tool in the ezyVet MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ezyVet MCP Server MCP server in PolicyLayer and add a rule for list_animals: 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 ezyVet MCP Server. Nothing to install.
list_animals 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 list_animals 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 list_animals. 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.
list_animals is provided by the ezyVet MCP Server MCP server (nobanks/ezyvet-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 →