AI agents call a11y_suggest_fix 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 reads from a knowledge base of accessibility remediation patterns and returns reference material to help users understand how to fix issues. It has no capability to execute code, modify user data, delete resources, or trigger external operations. The output is purely informational guidance, making it a Read category tool with low severity risk.
From the tool's definition Tool provides 'remediation patterns' and 'before/after code examples' — it retrieves and presents guidance rather than executing or modifying systems.
Attacks that exploit this kind of access
Get remediation patterns for accessibility issues. Includes before/after code examples and related patterns. 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_suggest_fix: 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_suggest_fix 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_suggest_fix 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_suggest_fix. 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_suggest_fix 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 →