Critique HTML → 10-dimension quality score
AI agents call critique_design to retrieve information from BWVI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and evaluates information about HTML design quality, producing a report or score. It does not create, modify, delete, or execute external code—it merely examines input and returns an assessment. This fits the Read category (queries/evaluates data with no side effects).
From the tool's definition Tool name and description indicate critique_design performs analysis (critique, scoring) on provided HTML without modification or side effects. The phrase 'quality score' and 'critique' are evaluative/analytical operations.
Documented attack patterns abuse exactly the kind of access critique_design gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BWVI, and nothing reaches the server without passing your rules. This is the rule we recommend for critique_design:
{
"version": "1",
"default": "deny",
"tools": {
"critique_design": {}
}
}critique_design 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.
Critique HTML → 10-dimension quality score. It is categorised as a Read tool in the BWVI MCP Server, which means it retrieves data without modifying state.
Register the BWVI MCP server in PolicyLayer and add a rule for critique_design: 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 BWVI. Nothing to install.
critique_design 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 critique_design 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 critique_design. 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.
critique_design is provided by the BWVI MCP server (lh123aa/bwvi-design). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BWVI, 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.
15 BWVI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.