AI agents call a11y_lookup_wcag 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 purely retrieves and returns reference information about WCAG criteria. It has no side effects, does not modify any data, and only queries a knowledge base to return structured information. Misuse potential is essentially nil.
From the tool's definition "Look up WCAG criteria by number, keyword, or level. Returns criterion details including description, techniques, failures, and test suggestions."
Attacks that exploit this kind of access
Look up WCAG criteria by number, keyword, or level. Returns criterion details including description, techniques, failures, and test suggestions. 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_lookup_wcag: 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_lookup_wcag 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_lookup_wcag 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_lookup_wcag. 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_lookup_wcag 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 →