AI agents call get_css_property_details 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 queries MDN documentation to fetch and return CSS property details (syntax, examples, use cases). It performs no data modification, deletion, code execution, or external state changes. The operation is a straightforward information lookup with negligible risk if misused by an AI agent.
From the tool's definition Tool 'retrieves comprehensive information about a CSS property from MDN documentation' — the verb 'retrieves' indicates a read-only query operation with no side effects.
Attacks that exploit this kind of access
Retrieves comprehensive information about a CSS property from MDN documentation including syntax, examples, and use cases. 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 get_css_property_details: 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.
get_css_property_details 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 get_css_property_details 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 get_css_property_details. 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.
get_css_property_details 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 →