Simulate screen reader navigation on a page. Tests page title, language, image alt text, link/button accessible names, form labels, and ARIA live regions. Use for WCAG 1.1.1, 1.3.1, 2.4.1, 2.4.4, 3.3.2, 4.1.2 checks. Set deep=true for AI-enhanced analysis (requires OPENAI_API_KEY).
AI agents call test_screen_reader to retrieve information from aria51 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation: it retrieves and analyzes accessibility metadata from web pages to produce diagnostic reports. It scans and queries without side effects. While it can be called repeatedly or configured with parameters, it remains fundamentally a non-destructive diagnostic tool that does not create, modify, delete, or execute code on the target system.
From the tool's definition Tool simulates screen reader navigation and tests accessibility criteria (page title, alt text, labels, ARIA regions).
Attacks that exploit this kind of access
Simulate screen reader navigation on a page. Tests page title, language, image alt text, link/button accessible names, form labels, and ARIA live regions. Use for WCAG 1.1.1, 1.3.1, 2.4.1, 2.4.4, 3.3.2, 4.1.2 checks. Set deep=true for AI-enhanced analysis (requires OPENAI_API_KEY). It is categorised as a Read tool in the aria51 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the aria51 MCP Server MCP server in PolicyLayer and add a rule for test_screen_reader: 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 aria51 MCP Server. Nothing to install.
test_screen_reader 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 test_screen_reader 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 test_screen_reader. 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.
test_screen_reader is provided by the aria51 MCP Server MCP server (justinleeirizarry/aria51). 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 →