AI agents call a11y_document_component to retrieve information from A11y without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates/reads documentation about UI components for accessibility purposes. It retrieves and presents information about keyboard interactions, ARIA attributes, and screen reader behavior. There are no side effects, data modifications, or destructive actions involved — it is purely informational output generation.
From the tool's definition Generate accessibility documentation for UI components. Includes keyboard interactions, ARIA attributes, and screen reader expectations.
Attacks that exploit this kind of access
Generate accessibility documentation for UI components. Includes keyboard interactions, ARIA attributes, and screen reader expectations. It is categorised as a Read tool in the A11y MCP Server, which means it retrieves data without modifying state.
Register the A11y MCP server in PolicyLayer and add a rule for a11y_document_component: 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 A11y. Nothing to install.
a11y_document_component 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 a11y_document_component 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 a11y_document_component. 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.
a11y_document_component is provided by the A11y MCP server (shawnmcb/a11y-mcp-server). 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 →