Run accessibility tests on raw HTML content and return violations in raw JSON format. [${configNote}]
AI agents call analyze_html_json to retrieve information from Accessibility Testing MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads HTML content, runs accessibility checks against it using axe-core/IBM Equal Access engines, and returns structured JSON results. It has no side effects on the HTML content, the website being tested, or any external systems. The test analysis itself is a read-only operation that produces diagnostic data.
From the tool's definition Tool performs accessibility analysis and testing, returning violation reports in JSON format. The verb 'analyze' and the output description ('return violations') indicate information retrieval with no modification of underlying data or systems.
Attacks that exploit this kind of access
Run accessibility tests on raw HTML content and return violations in raw JSON format. [${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_json: 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_json 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_json 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_json. 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_json 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 →