AI agents call list-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 reference data from the W3C WAI-ARIA specification without modifying, executing, or deleting anything. It is purely informational and presents no risk of unintended side effects even if misused by an AI agent—the worst outcome is receiving incomplete or irrelevant ARIA role information. No code execution, data modification, or irreversible actions are possible.
From the tool's definition Tool name 'list-roles' and description 'List all ARIA roles, optionally filtered by category' indicate a query operation that retrieves and returns data about ARIA role definitions. The filtering parameter is a read-only lookup, not a modification.
Attacks that exploit this kind of access
List all ARIA roles, optionally filtered by category. Categories: widget, composite, document, landmark, liveRegion, window, abstract. 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-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-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-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-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-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 →