AI agents call check-name-requirements 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 queries information from the W3C WAI-ARIA specification. It has no side effects—it simply looks up accessibility requirements and returns read-only data. The worst case of misuse would be incorrect validation advice, which has minimal blast radius. This is clearly a Read operation aligned with the other specification lookup tools on the server (get-role, get-attribute, etc.).
From the tool's definition Tool name 'check-name-requirements' and description indicate it queries ARIA specification data to determine if a role requires an accessible name and retrieves allowed methods for providing it. No modification, execution, or deletion of data occurs.
Attacks that exploit this kind of access
Check if a role requires an accessible name and how it can be provided. 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 check-name-requirements: 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.
check-name-requirements 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 check-name-requirements 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 check-name-requirements. 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.
check-name-requirements 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 →