AI agents call list-widget-roles to retrieve information from Aria without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates a set of predefined ARIA widget roles from specification data. It performs no modifications, deletions, or executions. The blast radius of misuse is minimal — an AI agent could only obtain reference information about ARIA roles, which is public specification data. This is a straightforward Read operation.
From the tool's definition Tool name is 'list-widget-roles' and description states it 'List all interactive widget roles' — a query operation that retrieves data from the W3C WAI-ARIA specification with no side effects.
Attacks that exploit this kind of access
List all interactive widget roles that represent user interface controls. It is categorised as a Read tool in the Aria MCP Server, which means it retrieves data without modifying state.
Register the Aria MCP server in PolicyLayer and add a rule for list-widget-roles: 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 Aria. Nothing to install.
list-widget-roles 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-widget-roles 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-widget-roles. 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-widget-roles is provided by the Aria MCP server (joe-watkins/aria-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 →