Validates HTML code for correct Material Web component usage
AI agents call validate_website to retrieve information from Material Web without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Validation is a read/analysis operation: it takes input HTML and checks it against Material Web rules, producing a report. No data is written, executed, or destroyed. Severity is low because the tool only processes user-supplied HTML strings with no external side effects.
From the tool's definition 'Validates HTML code for correct Material Web component usage' — the tool inspects/analyzes provided HTML and returns validation results
Attacks that exploit this kind of access
Validates HTML code for correct Material Web component usage. It is categorised as a Read tool in the Material Web MCP Server, which means it retrieves data without modifying state.
Register the Material Web MCP server in PolicyLayer and add a rule for validate_website: 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 Material Web. Nothing to install.
validate_website 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 validate_website 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 validate_website. 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.
validate_website is provided by the Material Web MCP server (shantoislamdev/material-web-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 →