AI agents call confirm_css_property_usage to retrieve information from Css First without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads consent status and retrieves implementation guidance from MDN documentation. It has no side effects on data or systems; it merely informs the user. The 'confirm' language refers to recording/acknowledging user consent, not executing an irreversible action. This is informational read-access to documentation and consent state.
From the tool's definition Tool 'confirms user consent' and 'provides implementation guidance' — it queries consent state and retrieves documentation. No creation, modification, deletion, code execution, or financial action occurs.
Attacks that exploit this kind of access
Confirms user consent for using a specific CSS property and provides implementation guidance. It is categorised as a Read tool in the Css First MCP Server, which means it retrieves data without modifying state.
Register the Css First MCP server in PolicyLayer and add a rule for confirm_css_property_usage: 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 Css First. Nothing to install.
confirm_css_property_usage 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 confirm_css_property_usage 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 confirm_css_property_usage. 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.
confirm_css_property_usage is provided by the Css First MCP server (luko248/css-first). 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 →