Run an axe-core accessibility audit on a URL. Reports WCAG violations grouped by impact
AI agents call analyze_accessibility to retrieve information from ToolCenter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries a URL and reports on accessibility metrics using axe-core (a standard accessibility scanning library). This is an information retrieval operation with no side effects on the target system or data. While it analyzes web content, it does not execute arbitrary code, create/modify/delete resources, or trigger external operations — it merely fetches and evaluates accessibility compliance.
From the tool's definition Tool performs an audit operation that 'Reports WCAG violations grouped by impact' — it retrieves and analyzes accessibility data from a URL without modifying, executing code on target systems, deleting data, or moving funds.
Attacks that exploit this kind of access
Run an axe-core accessibility audit on a URL. Reports WCAG violations grouped by impact. It is categorised as a Read tool in the ToolCenter MCP MCP Server, which means it retrieves data without modifying state.
Register the ToolCenter MCP server in PolicyLayer and add a rule for analyze_accessibility: 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 ToolCenter MCP. Nothing to install.
analyze_accessibility 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 analyze_accessibility 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 analyze_accessibility. 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.
analyze_accessibility is provided by the ToolCenter MCP server (toolcenter-dev/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 →