AI agents call get-attribute 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 and retrieves ARIA attribute metadata from the W3C specification—a read-only, informational operation with no side effects. There is no capability to modify attributes, execute code, delete data, or perform any destructive or financial actions. The blast radius of misuse is minimal; an AI agent cannot cause harm by querying ARIA attribute definitions.
From the tool's definition Tool name 'get-attribute' and description indicate retrieval of 'detailed information about an ARIA state or property' with no mention of modification, deletion, or execution of operations.
Attacks that exploit this kind of access
Get detailed information about an ARIA state or property (e.g., aria-label, aria-expanded, aria-hidden). 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 get-attribute: 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.
get-attribute 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 get-attribute 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 get-attribute. 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.
get-attribute 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 →