Run accessibility tests on raw HTML content. [${configNote}]
AI agents call analyze_html to retrieve information from Accessibility Testing MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes HTML content to generate accessibility compliance reports. It has no side effects—it does not modify the HTML, delete data, execute code with external impact, or commit financial obligations. The testing is purely analytical, placing it squarely in the Read category.
From the tool's definition Tool performs accessibility testing and analysis on HTML content, producing 'violation reports with remediation guidance' with no modification of any data or external systems.
Attacks that exploit this kind of access
Run accessibility tests on raw HTML content. [${configNote}]. It is categorised as a Read tool in the Accessibility Testing MCP MCP Server, which means it retrieves data without modifying state.
Register the Accessibility Testing MCP server in PolicyLayer and add a rule for analyze_html: 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 Accessibility Testing MCP. Nothing to install.
analyze_html 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_html 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_html. 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_html is provided by the Accessibility Testing MCP server (joe-watkins/accessibility-testing-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 →