AI agents call suggest-role 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 queries the W3C WAI-ARIA specification database to provide role recommendations based on input descriptions. It has no side effects, does not execute code, does not modify data, and does not perform destructive operations. It purely retrieves and suggests information, making it a Read operation with low severity and minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'suggest-role' and description 'Suggest appropriate ARIA roles based on a description of the UI component' indicate a query/suggestion operation that retrieves information from the ARIA specification without modifying, executing, or deleting…
Attacks that exploit this kind of access
Suggest appropriate ARIA roles based on a description of the UI component. 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 suggest-role: 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.
suggest-role 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 suggest-role 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 suggest-role. 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.
suggest-role 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 →