Check HTML/CSS/JS consistency and accessibility: file naming, class naming (BEM), vendor prefixes, responsive design, ARIA role validation, heading hierarchy, skip links, form label association, button types, tabindex.
AI agents call wpcs_frontend_check to retrieve information from WPCS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and reports on code quality metrics and accessibility compliance without executing code, modifying files, or triggering external operations. It belongs to the Read category as a static analysis and validation tool. Severity is low because misuse would only result in false positives or false negatives in reports, with no destructive or operational side effects.
From the tool's definition Tool performs "Check" operations on HTML/CSS/JS consistency and accessibility without modifying code. The description lists validation and inspection activities: file naming, class naming, vendor prefixes, responsive design, ARIA role validation, heading…
Documented attack patterns abuse exactly the kind of access wpcs_frontend_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WPCS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for wpcs_frontend_check:
{
"version": "1",
"default": "deny",
"tools": {
"wpcs_frontend_check": {}
}
} wpcs_frontend_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check HTML/CSS/JS consistency and accessibility: file naming, class naming (BEM), vendor prefixes, responsive design, ARIA role validation, heading hierarchy, skip links, form label association, button types, tabindex. It is categorised as a Read tool in the WPCS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WPCS MCP Server MCP server in PolicyLayer and add a rule for wpcs_frontend_check: 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 WPCS MCP Server. Nothing to install.
wpcs_frontend_check 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 wpcs_frontend_check 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 wpcs_frontend_check. 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.
wpcs_frontend_check is provided by the WPCS MCP Server MCP server (vapvarun/wpcs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WPCS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 WPCS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.