Compare two HTML files → metric diff report
AI agents call critique_diff 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 performs a read-only comparison between two HTML files and generates a report of metric differences. It retrieves and analyzes data without creating, modifying, executing, or deleting anything. The blast radius of misuse is minimal—a malicious agent could only generate unwanted diff reports or analyze files they shouldn't, not cause damage or side effects.
From the tool's definition Tool name 'critique_diff' and description 'Compare two HTML files → metric diff report' indicate a comparison/analysis operation that retrieves and reports differences. No modification, deletion, or execution of external code is implied.
Documented attack patterns abuse exactly the kind of access critique_diff 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_diff:
{
"version": "1",
"default": "deny",
"tools": {
"critique_diff": {}
}
}critique_diff 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.
Compare two HTML files → metric diff report. 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_diff: 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_diff 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_diff 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_diff. 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_diff 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.